LLMs are a compressed repository of a vast corpus of valuable information on which they are trained. Therefore, this work hypothesizes that LLMs such as Llama, Orca, Falcon, and Mistral can be used for misinformation detection by making them cross-check new information with the repository on which they are trained. Accordingly, this paper describes the findings from the investigation of the abilities of LLMs in detecting misinformation on multiple datasets. The results are interpreted using explainable AI techniques such as LIME, SHAP, and Integrated Gradients. The LLMs themselves are also asked to explain their classification. These complementary approaches aid in better understanding the inner workings of misinformation detection using LLMs and lead to conclusions about their effectiveness at the task.

The rise of abusive language on social media is a significant threat to mental health and 1 social cohesion. For Bengali speakers, the need for effective detection is critical. However, current 2 methods fall short in addressing the massive volume of content. Improved techniques are urgently 3 needed to combat online hate speech in Bengali. Traditional machine learning techniques, while 4 useful, often require large, linguistically diverse datasets to train models effectively. This paper 5 addresses the urgent need for improved hate speech detection methods in Bengali, aiming to fill the 6 existing research gap. Contextual understanding is crucial in differentiating between harmful speech 7 and benign expressions. Large language models (LLMs) have shown state-of-the-art performance in 8 various natural language tasks due to their extensive training on vast amounts of data. We explore the 9 application of LLMs, specifically GPT-3.5 Turbo and Gemini 1.5 Pro, for Bengali hate speech detection 10 using Zero-Shot and Few-Shot Learning approaches. Unlike conventional methods, Zero-Shot 11 Learning identifies hate speech without task-specific training data, making it highly adaptable to new 12 datasets and languages. Few-Shot Learning, on the other hand, requires minimal labeled examples, 13 allowing for efficient model training with limited resources. Our experimental results show that 14 LLMs outperform traditional approaches. In this study, we evaluated GPT-3.5 Turbo and Gemini 1.5 15 Pro on multiple datasets. To further enhance our study, we considered the distribution of comments 16 in different datasets and the challenge of class imbalance, which can affect model performance. The 17 BD-SHS dataset consists of 35,197 comments in the training set, 7,542 in the validation set, and 7,542 18 in the test set. The Bengali Hate Speech Dataset v1.0 & v2.0 includes comments distributed across 19 various hate categories: personal hate (629), political hate (1,771), religious hate (502), geopolitical hate 20 (1,179), and gender abusive hate (316). The Bengali Hate Dataset comprises 7,500 non-hate and 7,500 21 hate comments. GPT-3.5 Turbo achieved impressive results with 97.33%, 98.42%, and 98.53% accuracy. 22 In contrast, Gemini 1.5 Pro showed lower performance across all datasets. Specifically, GPT-3.5 Turbo 23 excelled with significantly higher accuracy compared to Gemini 1.5 Pro. These outcomes highlight a 24 6.28% increase in accuracy compared to traditional methods, which achieved 92.25%. Our research 25 contributes to the growing body of literature on LLM applications in natural language processing, 26 particularly in the context of low-resource languages.

Large Language Models (LLMs) have emerged as powerful tools in the domain of artificial intelligence, specifically enhancing natural language processing capabilities. These models leverage extensive datasets and sophisticated algorithms to automate and enhance tasks traditionally performed by humans, thereby revolutionizing innovation and entrepreneurship. LLMs accelerate product development, streamline business operations, and enable precise and rapid decision-making, all of which are crucial for maintaining competitiveness in dynamic markets. This paper categorizes the applications of LLMs in innovation and entrepreneurship into three main areas: technological innovation, strategic decision-making, and process automation. By exploring various integrations of LLMs in entrepreneurial ventures, this work offers both theoretical insights and practical examples, underscoring the transformative impact of LLMs in shaping modern business landscapes.

Large Language Models (LLMs) like GPT-4 and mBERT have revolutionized natural languageprocessing (NLP) by providing multilingual capabilities, making it possible to develop models thathandle diverse linguistic inputs across various languages. However, despite these advances, thereremains a noticeable performance gap between how well these models perform in high-resourcelanguages such as English and low-resource languages such as Nepali or Malagasy. We term thisphenomenon the "Babel Effect," highlighting the disproportionate performance that arises fromdifferences in resource availability across languages.This paper aims to explore the root causes of these performance discrepancies in LLMs, focusingon the underlying challenges in tokenization, training, and data scarcity. We utilize cross-lingualbenchmarks, such as XGLUE and TyDiQA, to quantify these performance variations and examinethem in detail. Furthermore, we propose solutions, including enhancing tokenization strategies,employing data augmentation techniques, and refining fine-tuning methods. The paper concludeswith a discussion on how these improvements can mitigate the Babel Effect and lead to more equitablelanguage modeling across diverse linguistic contexts.

Kinetic modeling is an essential tool in systems biology research, enabling the quantitative analysis of biological systems and predicting their behavior. However, the development of kinetic models is a complex and time-consuming process. In this article, we propose a novel approach called KinModGPT, which generates kinetic models directly from natural language text. KinModGPT employs GPT-3 as a natural language interpreter and Tellurium as an SBML generator. We demonstrate the effectiveness of KinModGPT in creating SBML models from complex natural language descriptions of biochemical reactions. KinModGPT successfully generates valid SBML models from a range of natural language model descriptions of metabolic pathways, protein-protein interaction networks, and heat shock response. This article demonstrates the potential of KinModGPT in kinetic modeling automation.

Current language models have achieved remarkable success in NLP tasks. Nonetheless, individual decoding methods face difficulties in realizing the immense potential of these models. The challenge is primarily due to the lack of a decoding framework that can integrate language models and decoding methods. We introduce the DecoStrat which bridges the gap between language modeling and the decoding process in D2T generation. By leveraging language models, DecoStrat facilitates the exploration of alternative decoding methods tailored to specific tasks. We fine-tune the model on the MultiWOZ dataset to meet task-specific requirements and employ it to generate output(s) through multiple interactive modules of the framework. The Director module orchestrates the decoding processes, engaging the Generator to produce output(s) text based on the selected decoding method and input data. The Manager module enforces a selection strategy, integrating Ranker and Selector to identify the optimal result. Evaluations on the stated dataset show that DecoStrat effectively produces diverse and accurate output, with MBR variants consistently outperforming other methods. DecoStrat with the T5-small model surpasses some baseline. Generally, the findings highlight DecoStrat's potential for optimizing decoding methods in diverse real-world applications.

Sentiment analysis is a technique used to understand the publics’ opinion towards an event, product, or organization. For example, positive or negative opinion or attitude towards electric vehicle (EV) brands. This provides companies with valuable insight about the public's opinion of their products and brands. In the field of natural language processing (NLP), transformer models have shown great performances over the traditional machine learning algorithms. However, these models have not been explored extensively in the EV domain. EV companies are becoming signif-icant competitors in the automotive industry and are projected to cover up to 30% of the United States light vehicle market by 2030 [1]. In this study, we present a comparative study of large language models (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimized BERT approach and generalized autoregressive pretraining for language un-derstanding using Lucid motors and Tesla motors YouTube datasets. Results evidenced LLMs like BERT and her variants are off-the-shelf algorithms for sentiment analysis, specifically, when fi-ne-tuned. Furthermore, our findings presents the need for domain adaptation whilst utilizing LLMs. Finally, the experimental results showed that RoBERTa achieved consistent performance across the EV datasets with a F1 score of at least 92%.

This survey provides a comprehensive overview of in-context learning (ICL) in large language models (LLMs), a phenomenon where models can adapt to new tasks without parameter updates by leveraging task-relevant information within the input context. We explore the definition and mechanisms of ICL, investigate the factors contributing to its emergence, and discuss strategies for optimizing and effectively utilizing ICL in various applications. Through a systematic review of recent literature, we first clarify what ICL is, distinguishing it from traditional fine-tuning approaches and highlighting its unique characteristics. We then delve into the underlying causes of ICL, examining theories ranging from implicit meta-learning during pre-training to the emergence of task vectors in LLMs. The survey also covers various approaches to enhance ICL performance, including prompt engineering techniques, demonstration selection strategies, and methods for improving generalization across diverse tasks. Additionally, we discuss the limitations and challenges of ICL, such as its sensitivity to demonstration ordering and potential biases. By synthesizing findings from numerous studies, we aim to provide researchers and practitioners with a clear understanding of the current state of ICL research, its practical implications, and promising directions for future investigation. This survey serves as a valuable resource for those seeking to leverage ICL capabilities in LLMs and contributes to the ongoing discourse on the remarkable adaptability of these models.

In this paper, we propose "Synergized Efficiency Optimization for Large Language Models" (SEO-LLM), a groundbreaking approach that integrates advanced data utilization and model compression techniques to significantly enhance the performance, efficiency, and scalability of large language models (LLMs). Our method synergistically combines Adaptive Data Augmentation (ADA), Transfer- Active Learning (TAL), Adaptive Iterative Pruning (AIP), and Synergistic Quantization and Distillation (SQD). These components work together to reduce the training data requirement by 30%, compress model size by 67.6%, and improve inference speed by up to 50%, while preserving or even enhancing model accuracy across various NLP tasks. ADA dynamically adjusts augmentation strategies to optimize model generalization, while TAL leverages pre-trained models to focus learning on the most informative data samples. AIP intelligently prunes less significant weights, and SQD harmonizes quantization with knowledge distillation to achieve high compression rates without significant performance loss. The synergy between these techniques makes SEO-LLM a robust solution for deploying LLMs in resource-constrained environments, maintaining state-of-the-art performance with a fraction of the computational and data resources.

The increased complexity of modern systems is calling for an integrated and comprehensive approach to system design and development and in particular, a shift towards Model-Based Systems Engineering (MBSE) approaches for system design. The requirements that serve as the foundation for these intricate systems are still primarily expressed in Natural Language (NL), which can contain ambiguities and inconsistencies that hinder their direct translation into models. The colossal developments in the field of Natural Language Processing (NLP) in general and Large Language Models (LLMs) in particular can serve as an enabler for the conversion of NL requirements into semi-machine-readable requirements. This is expected to facilitate their standardization and use in a model-based environment. This paper discusses a two-fold strategy for converting NL requirements into semi-machine-readable requirements using language models. The first approach involves creating a requirements table by extracting information from free-form NL requirements. The second approach is an agile methodology that facilitates the identification of boilerplate templates for different types of requirements based on observed linguistic patterns. For this study, three different LLMs were utilized. Two of these models were fine-tuned versions of Bidirectional Encoder Representations from Transformers (BERT), specifically aeroBERT-NER and aeroBERT-Classifier, which were trained on annotated aerospace corpora. Another LLM, called flair/chunk-english, was utilized to identify sentence chunks present in NL requirements. All three language models were utilized together to achieve the standardization of requirements. To demonstrate the effectiveness of the methodologies, requirements from Parts 23 and 25 of Title 14 Code of Federal Regulations (CFRs) were employed, and a total of two, five, and three boilerplate templates were identified for design, functional, and performance requirements, respectively.

This project aims to create a virtual assistant with AI integration to improve Siemens Energy's internal processes. Using cloud-based technologies, microservice architecture, and large language models (LLMs), the project seeks to create a reliable, effective, and user-friendly assistant customized to Siemens Energy's requirements. The first significant business difficulty identified by the study was the time engineers had to spend looking for information in large volumes of company papers. The proposed virtual assistant responds with precision and context awareness to optimize productivity. The assistant uses a microservice architecture to guarantee scalability, flexibility, and integration for various use scenarios. Tasks like document retrieval, translation, summarization, and comparison can now be handled effectively. Utilizing Amazon Web Services (AWS) for cost-effectiveness and scalability, the backend is cloud-deployed, backed by a frontend created for natural user interaction. To increase precision and relevance, the system uses cutting-edge AI, such as vector databases and Retrieval Augmented Generation (RAG). The assistant expedites document management procedures, improves data accessibility, and reduces search time. The results highlight how it may enhance workflow efficiency for Siemens Energy engineers and how flexible it can be for future AI-driven applications.

Natural language Processing (NLP) has significantly transformed in the last decade, especially in the field of Language Modeling. Large Language Models (LLMs) have achieved SOTA performances on Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks by learning language representation in self-supervised ways. This paper provides a comprehensive survey to capture the progression of advances in Language Models. In this paper, we examine the different aspects of Language Models, which started with a few million parameters but have reached the size of a trillion in a very short time. We also look at how these LLMs transitioned from task-specific to task-independent to task-and-language-independent architectures. This paper extensively discusses different pre-training objectives, benchmarks, and transfer learning methods used in LLMs. It also examines different fine-tuning and In-Context learning techniques used in downstream tasks. It also explores how LLMs can perform well across many domains and datasets if sufficiently trained on a large and diverse dataset. Next, it discusses how, over time, the availability of cheap computational power and large datasets have improved LLM’s capabilities and raised new challenges. As part of our study, we also inspect LLMs from the lens of scalability to see how their performance is affected by the model’s depth, width, and data size. Lastly, we provide an empirical comparison of existing trends and techniques and a comprehensive analysis of where the field of LLM currently stand.

Large language models have recently made significant progress in natural language processing, and there is observation that these models exhibit reasoning abilities when they are sufficiently large. This has sparked considerable research interest since reasoning is a hallmark of human intelligence that is widely considered missed in artificial intelligence systems. Due to large size of these models, evaluation of LLMs’ reasoning ability is largely empirical. Creating datasets to evaluate the reasoning ability of LLMs is therefore an important area of LLM research. A key open question is whether LLMs reason or simply recite memorized texts they have encountered during their training phase. This work conducts simple experiments using Cheryl’s Birthday Puzzle and Cheryl’s Age Puzzle and their variants created in this work to investigate whether LLMs recite or reason and discovers that LLMs tend to recite memorized answers for well-known questions, which appear more frequently on the internet, even though such answers may not be sensible for the modified versions of the questions. When presented with less well-known questions, it is observed that LLMs answer with correct reasoning more frequently. A possible inference is that LLMs tend to reason on less well-known questions but recite memorized answers on popular questions. As a result, to accurately evaluate the reasoning ability of LLMs, it is essential to create new datasets to ensure that LLMs are elicited to truly use their reasoning ability to generate responses to the presented questions. In view of the finding, this work proposes a new dataset comprising of unseen questions requiring semantic and deductive logical reasoning skills to elicit reasoning ability from LLMs. The proposed evaluation framework is based on the intuition that some questions or puzzles can only be answered through the mastery of reasoning needed for situational awareness, and the dataset consists of 84 logical reasoning questions on room assignment subject to constraints. The proposed evaluation framework has several desirable properties, including resilience to training data contamination, ease of response verification, extensibility, usefulness and automated test case generation. This work then applies the proposed dataset to evaluate the reasoning ability of state-of-the-art LLMs, including GPT-3, GPT-4, Llama-3.1, Gemini-1.5 and Claude-3.5, and compare their performance with the performance of human intelligence on the dataset.

This paper presents our approaches for the SMM4H’24 Shared Task 5 on the binary classification of English tweets reporting children’s medical disorders. Our first approach involves fine-tuning a single RoBERTa-large model, while the second approach entails ensembling the results of three fine-tuned BERTweet-large models. We demonstrate that although both approaches exhibit identical performance on validation data, the BERTweet-large ensemble excels on test data. Our best-performing system achieves an F1-score of 0.938 on test data, outperforming the benchmark classifier by 1.18%.

Although learning analytics (LA) holds great potential to improve teaching and learning, LA research and practice are currently riddled with limitations that impact every stage of the LA life cycle. The present paper offers an overview of these challenges before proposing strategies to overcome them and exploring how the recent innovations brought forth by language models can improve LA research and practice. In particular, we encourage the empowerment of teachers during LA development, as this would strengthen the theoretical foundation of LA solutions and increase their interpretability and usability. Furthermore, we provide examples of how process data can be used to understand learning processes and generate more interpretable LA insights. Furthermore, we explore how LLMs could come into play in LA to generate interpretable insights, timely and actionable feedback, increase personalization, and support teachers’ tasks more broadly.

Biomedical large language models (LLMs) have made significant strides, but their reliance on external retrieval mechanisms presents challenges in accuracy and computational efficiency. To address these issues, we propose MedRAG-Refine, a generative LLM designed specifically for the biomedical domain. Our model integrates a two-stage fine-tuning process, incorporating a self-reflection mechanism to improve reasoning quality. We evaluate our model on MedQA, MedMCQA, and MMLU datasets, demonstrating superior performance over state-of-the-art methods. Additionally, human evaluations confirm the enhanced accuracy and reasoning quality of our model in real-world medical tasks.

The growing dependence on large language models (LLM)s highlights the urgent need to deepen trust in these technologies. Regular, rigorous validation of their expertise, especially in nuanced and intricate scenarios, is essential to ensure their readiness for clinical applications. Our study pioneers the exploration of LLM utility in the field of cardiology. We stand at the cusp of a transformative era where mature AI and LLMs, notably ChatGPT, GPT-4, and Google Bard, are poised to influence healthcare significantly. Recently, we put three available LLMs, OpenAI's ChatGPT-3.5, GPT-4.0, and Google's Bard, to the test against a significant Polish medical special-ization licensing exam (PES). The exams cover the scope of completed specialist training, focusing on diagnostic and therapeutic procedures, excluding invasive medical procedures and interven-tions. In our analysis, GPT-4 consistently outperformed the others, ranking first, with and Google Bard and ChatGPT- 3.5 following, respectively. The performance metrics underscore GPT-4's no-table potential in medical applications. Given a score improvement of over 23.5 % between two AI models released just four months apart, clinicians must stay informed and up-to-date about these rapidly evolving tools and their potential applications to clinical practice. Our results provide a snapshot of the current capabilities of these models, highlighting the nuanced performance dif-ferences when confronted with identical questions

This paper examines the potential of large language models, specifically ChatGPT, BingChat, and Bard, in enhancing the work of teachers in various educational settings. These models, powered by cutting-edge artificial intelligence, offer a wide range of applications that can aid educators in curriculum development, personalized instruction, student engagement, and administrative tasks. By harnessing the capabilities of these language models, teachers can not only streamline their workload but also improve the overall quality of education. This paper explores the ways in which these models can empower educators and revolutionize teaching practices.

Although large language models demonstrate impressive capabilities, they sometimes generate irrelevant or nonsensical text, or produce outputs that deviate from the provided source input—an occurrence commonly referred to as hallucination. To mitigate this issue, we introduce a novel decoding method that incorporates both factual and hallucination prompts(DFHP), utilizing a contrastive output distribution to highlight the disparity in output probabilities between model predictions influenced by factual prompts and those affected by hallucination prompts. Experiments on both multiple-choice and text generation tasks show that our approach significantly enhances the factual accuracy of large language models without requiring additional training.

Humans have a unique cognitive ability known as relational abstraction, which allows us to identify logical rules and patterns beyond basic perceptual characteristics. This ability represents a key difference between how humans and other animals learn and interact with the world. With current large language models rivaling human intelligence in many regards, we investigated whether relational abstraction was an emergent chat completion capacity in various models. We find that despite their impressive language processing skills, all tested language models failed the relational match-to-sample (RMTS) test, a benchmark for assessing relational abstraction. These results challenge the assumption that advanced language skills inherently confer the capacity for complex relational reasoning. The paper highlights the need for a broader evaluation of AI cognitive abilities, emphasizing that language proficiency alone may not be indicative of certain higher-order cognitive processes thought to be supported by language.

(1) Background: Artificial Intelligence (AI) models have shown potential in various educational contexts. However, their utility in explaining complex biological phenomena, such as Intrinsically Disordered Proteins (IDPs), requires further exploration. This study empirically evaluated the performance of various Large Language Models (LLMs) in the educational domain of IDPs. (2) Methods: Four LLMs, GPT-3.5, GPT-4, GPT-4 with Browsing, and Google Bard (PaLM 2), were assessed using a set of IDP-related questions. An expert evaluated their responses across five categories: accuracy, relevance, depth of understanding, clarity, and overall quality. Descriptive statistics, ANOVA, and Tukey's honesty significant difference tests were utilized for analysis. (3) Results: The GPT-4 model consistently outperformed the others across all evaluation categories. Although GPT-4 and GPT-3.5 were not statistically significantly different in performance (p>0.05), GPT-4 was preferred as the best response in 13 out of 15 instances. The AI models with browsing capabilities, GPT-4 with Browsing and Google Bard (PaLM 2) displayed lower performance metrics across the board with statistically significant differences (p<0.0001). (4) Conclusion: Our findings underscore the potential of AI models, particularly LLMs such as GPT-4, in enhancing scientific education, especially in complex domains such as IDPs. Continued innovation and collaboration among AI developers, educators, and researchers are essential to fully harness the potential of AI for enriching scientific education.

Patient symptoms play a critical role in disease progression and diagnosis, yet they are most often captured in unstructured clinical notes. This study explores use of large language models (LLMs) for extracting patient symptoms from clinical notes, comparing their performance against rule-based information extraction (IE) systems, like BioMedICUS. By fine-tuning an LLM on diverse corpora from multiple healthcare institutions, we aimed to improve symptom extraction accuracy and efficiency with symptoms related to acute and post-acute sequelae of SARS-CoV-2. We also conducted prevalence analysis to highlight significant differences in symptom prevalence across corpora and performed fairness analysis to assess the model's equity across race and gender. Our findings indicate that while LLMs can match the effectiveness of rule-based IE methods, they face significant challenges related to demographic bias and generalizability due to variability in training corpora. This evaluation revealed overfitting and insufficient generalization, especially when models were trained predominantly on limited datasets with single annotator bias. This study also revealed that LLMs offer substantial advantages in efficiency, adaptability, and scalability for biomedical IE, marking a transformative shift in clinical data extraction processes. These results provide real-world evidence of the necessity for diverse, high-quality training datasets and robust annotation processes to enhance LLM’s performance and reliability in clinical applications.

In light of the self-simulation hypothesis, a simple form implementation of the principle of efficient language is discussed in a self-referential geometric quasicrystalline state sum model in three dimensions. Emergence is discussed in context of geometric state sum models.

The pursuit of Artificial Intelligence (AI) that emulates human cognitive processes is a cornerstone of ethical AI development, ensuring that emerging technologies can integrate seamlessly into societal frameworks requiring nuanced understanding and decision-making. Zero-Shot Instance Retrieval (ZSIR) stands at the forefront of this endeavour, potentially providing a robust platform for AI systems, particularly large visual language models, to demonstrate and refine cognition-aligned learning without the need for direct experience. In this paper, we critically evaluate current cognition alignment methodologies within traditional zero-shot learning paradigms, using visual attributes and word embedding generated by large AI models. We propose a unified similarity function that quantifies the cognitive alignment level, bridging the gap between AI processes and human-like understanding. Through extensive experimentation, our findings illustrate that this similarity function can effectively mirror the visual-semantic gap, steering the model towards enhanced performance in zero-shot instance retrieval. This work not only benchmarks the cognition alignment of AI, but also sets a new precedent for the development of visual language models attuned to the complexities of human cognition.}

Cognitive Warfare (CogWar) is another form of warfare where the goal is to exploit cognition facets to disrupt, undermine, influence or modify human decisions. Famous examples include “Operation Gidlock” meddling with the US 2016 election, and CogWar campaigns assisting the annexation of Crimea. As Large Language Model(LLM)-based applications expand, reaching more users and their cognitive states, stealth Malicious Cognitive Behavioral Tactics (MCBT) can be embedded in trusted application sessions to systematically profile, then alter, each individual’s cognition over time. Successful MCBT can create more cases like Snowden, mass shootings, or January6. This short-form paper discusses a novel MCBT threat model, a novel kill chain, and an on-going prototype for demonstration.

This paper proposes the utilization of large language models as recommendations systems for museums. Since the aforementioned models lack the notion of context, they can’t work with temporal information that is often present in recommendations for cultural environments (e.g. special exhibitions or events). In this respect, the current work aims at enhancing the capabilities of large language models through a fine-tuning process that incorporates contextual information and user instructions. The resulting models are expected to be capable of providing personalized recommendations, aligned with user preferences and desires. More specifically, Generative Pre-trained Transformer 4, a knowledge-based large language model is fine-tuned and turned into a context-ware recommendation system, adapting its suggestions based on user input and specific contextual factors such as location, time of visit, and other relevant parameters. The effectiveness of the proposed approach is evaluated through certain user studies, which ensure an improved user experience and engagement within the museum environment.

Large Language Models (LLMs) have demonstrated promising capabilities to solve complex tasks in critical sectors such as healthcare. However, LLMs are limited by their training data which is often outdated, the tendency to generate inaccurate ("hallucinated") content and a lack of transparency in the content they generate. To address these limitations, retrieval augmented generation (RAG) grounds the responses of LLMs by exposing them to external knowledge sources. However, in the healthcare domain there is currently a lack of systematic understanding of which datasets, RAG methodologies and evaluation frameworks are available. This review aims to bridge this gap by assessing RAG-based approaches employed by LLMs in healthcare, focusing on the different steps of retrieval, augmentation and generation. Additionally, we identify the limitations, strengths and gaps in the existing literature. Our synthesis shows that proprietary models such as GPT-3.5/4 are the most used for RAG applications in healthcare. Also, there is a lack of standardized evaluation frameworks for RAG-based applications. In addition, the majority of the studies do not assess or address ethical considerations related to RAG in healthcare. It is important to account for ethical challenges that are inherent when AI systems are implemented in the clinical setting. Lastly, we highlight the need for further research and development to ensure responsible and effective adoption of RAG in the medical domain.

This study explores the enhancement of deductive reasoning capabilities in Large Language Models (LLMs) through a strategic dual-agent framework. In this framework, one agent acts as a questioner and another as an answerer, with both employing advanced linguistic and logical processing to optimize information exchange. Utilizing a structured environment that limits query opportunities, our approach emphasizes the development of LLMs that can efficiently generate and interpret questions to deduce hidden information effectively. The models, which incorporate self-defined agents with a combination of pretraining and llama-3-8b enhancements, demonstrate a remarkable ability to navigate the complexities of logical deduction. Performance evaluations, based on a series of simulated interactions, illustrate the agents' improved precision and strategic acumen in narrowing down possibilities through targeted inquiries. These findings underscore the potential of LLMs in tasks requiring intricate reasoning and collaboration, marking a significant step towards more intelligent and autonomous systems.

Structured science summaries or research contributions using properties or dimensions beyond traditional keywords enhances science findability. Current methods, such as those used by the Open Research Knowledge Graph (ORKG), involve manually curating properties to describe research papers' contributions in a structured manner, but this is labor-intensive and inconsistent between the domain expert human curators. We propose using Large Language Models (LLMs) to automatically suggest these properties. However, it's essential to assess the readiness of LLMs like GPT-3.5, Llama 2, and Mistral for this task before application. Our study performs a comprehensive comparative analysis between ORKG's manually curated properties and those generated by the aforementioned state-of-the-art LLMs. We evaluate LLM performance through four unique perspectives: semantic alignment and deviation with ORKG properties, fine-grained properties mapping accuracy, SciNCL embeddings-based cosine similarity, and expert surveys comparing manual annotations with LLM outputs. These evaluations occur within a multidisciplinary science setting. Overall, LLMs show potential as recommendation systems for structuring science, but further finetuning is recommended to improve their alignment with scientific tasks and mimicry of human expertise.

Large language models (LLMs) excel in providing natural language responses that sound authoritative, reflect knowledge of the context area, and can present from a range of varied perspectives. Agent Based Models and Simulation consist of simulated agents that interact within a simulated environment to explore societal, social, and ethical, among other, problems. Agents generate large volumes of data over time and discerning useful and relevant content is an onerous task. LLMs can help in communicating agents’ perspectives on key events by providing natural language narratives. However, these narratives need to be factual, transparent, and reproducible. To this end, we present a structured narrative prompt for sending queries to LLMs. Chi-square tests and Fisher’s Exact tests are applied to assess statistically significant difference in sentiment scores of the narrative messages between simulation generated narratives, ChatGPT-generated narratives, and real tweets. The narrative prompt structure effectively yields narratives with the desired components from ChatGPT. This structure is expected to be extensible across LLMs. In 14 out of 44 categories, ChatGPT generated narratives which has sentiment scores that were not discernibly different, in terms of statistical significance (alpha level of 0.05), from the sentiment expressed in real tweets. Three outcomes are provided: (1) a list of benefits and challenges for LLMs in narrative generation; (2) a structured prompt for requesting narratives of a LLM based on simulated agents’ information; and (3) an assessment of statistical significance in the sentiment prevalence of the generated narratives compared to real tweets. This indicates significant promise in the utilization of LLMs for helping to connect simulated agent’s experiences with real people.

With the rapid growth of large language models (LLMs), there is increasing demand for memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to reduce the model size and computation requirements, yet the performance is still sub-optimal. In this paper, we present a plug-and-play solution for post-training pruning of LLMs. The proposed solution has two innovative components: 1) Relative Importance and Activations (RIA), a new pruning metric that jointly considers the weight and activations efficiently on LLMs; and 2) Channel Permutation, a new approach to maximally preserve important weights under N:M sparsity. The two proposed components can be readily combined to further enhance the N:M semi-structured pruning of LLMs. Our empirical experiments show that RIA alone can already surpass all existing post-training pruning methods on prevalent LLMs, e.g., LLaMA ranging from 7B to 65B. Furthermore, N:M semi-structured pruning with channel permutation can even outperform the original LLaMA2-70B on zero-shot tasks, together with practical speed-up on specific hardware. Our code is available at: https://github.com/biomedical-cybernetics/Relative-importance-and-activation-pruning

Accurate crop diseases classification is crucial for ensuring food security and enhancing agricultural productivity. However, existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhances multimodal synergy for better crop disease classification than traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to using solely the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing prompt quality. Secondly, we integrate the cross-attention and the SE (Squeeze-and-Excitation) attention into the training-free mode VLCD (Vision-Language model for Crop Diseases classification) and the training-required mode VLCD-T (VLCD-Training) respectively for prompt text processing, enhancing classifier weights by emphasizing key text features. Experimental outcomes conclusively prove our method’s heightened classification effectiveness in few-shot crop disease scenarios, tackling data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process sensitive information such as personal communications and confidential documents. In this study, we propose a method for training NLP models on encrypted text data to mitigate data privacy concerns while maintaining similar performance to models trained on non-encrypted data. We demonstrate our method using two different architectures, namely Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups dataset. Our results indicate that both encrypted and non-encrypted models achieve comparable performance, suggesting that our encryption method is effective in preserving data privacy without sacrificing model accuracy. In order to replicate our experiments, we have provided a Colab notebook at the following address: https://t.ly/lR-TP

Obsessive-Compulsive Disorder (OCD) is a mental health condition marked by recurrent intrusive thoughts or sensations that compel individuals to perform repetitive behaviors or mental acts. Obsessions and compulsions significantly disrupt daily life and cause considerable distress. Early identification and intervention improve long-term outcomes. This study aimed to evaluate the ability of four advanced artificial intelligence models (ChatGPT-3.5, ChatGPT-4, Claude, and Bard) to accurately recognize OCD compared to human professionals and to assess recommended therapies and stigma attributions. This study was conducted during March 2024 utilizing 12 vi-gnettes. Each vignette depicted a client, either a young adult or a middle-aged male or female, attending an initial therapy session. Each vignette was evaluated ten times, resulting in 480 evaluations. The results were compared with those of a human sample of 514 psychotherapists, as reported by Canavan. Significant differences were found. AI models demonstrated higher OCD recognition rates and confidence levels than human professionals and showed 100% confidence in recognition, compared to 87% among psychotherapists. AI models also recommended evi-dence-based interventions more frequently, with ChatGPT-3.5 and Claude at 100%, ChatGPT-4 at 90%, and Bard at 60%, compared to 61.9% among psychotherapists. Additionally, AI models ex-hibited significantly lower stigma and danger estimations, though both AI and psychotherapists demonstrated high willingness to treat the described cases. The findings suggest that AI models surpass human professionals in recognizing OCD and recommending evidence-based treatments while also demonstrating lower stigma. These results highlight the potential of AI tools to enhance OCD diagnosis and treatment in clinical settings.

Over the years, machine learning has emerged as a tool for automated translation and has been studied relentlessly for decades. RBMT, SMT, and NMT models have been used to achieve machine translation and the results have drastically improved from when research in this field first began. Although a few general-purpose translators such as Google Translate or Microsoft Translator have accurate translations compared to that of a human translator, many pieces of text containing highly technical terms or homonyms are often mistranslated completely. When considering the necessity and importance of translating technical patents from different domains, accuracy in translation is not something that can be compromised. This motivates the need to improve the performance of machine translation further. The scope of this paper covers three open-source machine translation models for the purpose of patent documentation translation from English to Japanese, evaluates their performance on patent data, and proposes a methodology that enabled us to improve one of the model’s BLEU score by 41.22%, achieving a BLEU score of 46.18.

This study leverages transformer-based models and focuses on data representation strategies in the named entity recognition task, including "single" (one sentence per vector), "merged" (multiple sentences per vector), and "context" (sentences joined with attention to context). Performance analysis reveals that models trained with a single strategy may not perform well on different data representations. A combined training procedure is proposed to address this limitation, using all three strategies to enhance the stability and adaptability of the model. The results of this approach are presented and discussed for various datasets for four languages (English, Polish, Czech, and German), demonstrating the effectiveness of the combined strategy.

For any molecule, network, or process of interest, to keep up with new publications on these, is becoming increasingly difficult. For many cellular processes, molecules and their interactions that need to be considered can be very large. Automated mining of publications can support large scale molecular interaction maps and database curation. Text mining and Natural Language Processing (NLP)-based techniques are finding their applications in mining the biological literature, handling problems such as Named Entity Recognition (NER) and Relationship Extraction (RE). Both rule-based and machine learning (ML)-based NLP approaches have been popular in this context, with multiple research and review articles examining the scope of such models in Biological Literature Mining (BLM). In this review article, we explore self-attention based models, a special type of neural network (NN)-based architectures that have recently revitalized the field of NLP, applied to biological texts. We cover self-attention models operating either at a sentence level or an abstract level, in the context of molecular interaction extraction, published from 2019 onwards. We conduct a comparative study of the models in terms of their architecture. Moreover, we also discuss some limitations in the field of BLM that identifies opportunities for the extraction of molecular interactions from biological text.

ChatGPT, a Large Language Model (LLM) utilizing Natural Language Processing (NLP), has caused concerns about its impact on job sectors, including cybersecurity. In this study, we assessed ChatGPT’s impacts in non-managerial cybersecurity roles using the NICE Framework and Technological Displacement theory. We also explored its potential in passing top cybersecurity certification exams. Findings revealed ChatGPT’s promise in streamlining some jobs, especially those requiring memorization. Moreover, we highlighted ChatGPT’s challenges and limitations, such as ethical implications, LLM limitations, and Artificial Intelligence (AI) security. The study suggests that LLMs like ChatGPT could transform the cybersecurity landscape, causing job losses, skill obsolescence, labor market shifts, and mixed socioeconomic impacts. We recommend a shift in focus from memorization to critical thinking, and collaboration between LLM developers and cybersecurity professionals.

The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the complexity and volume of this data present substantial challenges in data modeling and analysis, which have been tamed with approaches spanning time series modeling to deep learning techniques. The latest frontier in this domain is the adoption of Large Language Models (LLMs), such as GPT-4 and Llama, for data analysis, modeling, understanding, and generation of human behavior through the lens of wearable sensor data. This survey explores current trends and challenges in applying LLMs for sensor-based human activity recognition and behavior modeling. We discuss the nature of wearable sensors data, the capabilities and limitations of LLMs to model them and their integration with traditional machine learning techniques. We also identify key challenges, including data quality, computational requirements, interpretability, and privacy concerns. By examining case studies and successful applications, we highlight the potential of LLMs in enhancing the analysis and interpretation of wearable sensors data. Finally, we propose future directions for research, emphasizing the need for improved preprocessing techniques, more efficient and scalable models, and interdisciplinary collaboration. This survey aims to provide a comprehensive overview of the intersection between wearable sensors data and LLMs, offering insights into the current state and future prospects of this emerging field.

Large language models (LLMs) have shown impressive performance and versatility. However, their billions of parameters and high computational costs hinder the development of personalized and privacy-preserving AI assistants operating locally on user devices. In this work, we explored the potential of pruning LLMs to create lightweight models suitable for user devices, using the moderate-sized Llama-2 7B model as an example. By adopting a simple yet effective pruning method, we found that up to 60% of the weights in the Llama-2 7B model could be pruned without significantly impairing its language modeling capabilities. Furthermore, despite occasional factual inaccuracies, the pruned model at the sparsity limit generated fluent and helpful answers to daily queries, demonstrating its feasibility of on-device AI assistants. These inaccuracies might originate from forgetting or hallucination due to pruning. We proposed a simple protocol to distinguish between the two mechanisms, as well as future directions to improve the pruned models for local AI assistants.

Large language models (LLMs) are essential to the field of natural language processing, and as their applications expand, security risks have become increasingly prominent. This paper introduces a novel benchmark for evaluating LLMs security, termed CS-Eval, designed to effectively assess the models' ability to address vulnerabilities. CS-Eval targets seven key security risks: ethical dilemmas, marginal topics, error detection, detailed event handling, cognitive bias, logical reasoning, and privacy identification, and establishes a Multi-Security Hazard Dataset (MSHD). The evaluated models include GPT-4o, Llama-3-70B, Claude-3-Opus, ERNIE-4.0, Abab-6.5, Qwen1.5-110B, Gemini-1.5-Pro, Doubao-Pro, SenseChat-V5, and GLM-4. We analyzed each model's performance in relation to these security risks and provided recommendations for improvement. Experimental results demonstrate varying levels of effectiveness across models, with GPT-4o exhibiting the best overall performance. Moreover, the relationship between security enhancement and model capa-bility is nonlinear, indicating that improving safety requires a multifaceted approach, considering various factors in both development and application.

The rapid increase in unstructured data across various fields has made multi-document comprehension and summarization a critical task. Traditional approaches often fail to capture relevant context, maintain logical consistency, and extract essential information from lengthy documents. This paper explores the use of Long-context Large Language Models (LLMs) for multi-document summarization, demonstrating their exceptional capacity to grasp extensive connections, provide cohesive summaries, and adapt to various industry domains and integration with enterprise applications/systems. The paper discusses the workflow of multi-document summarization for effectively deploying long-context LLMs, supported by case studies in legal applications, enterprise functions such as HR, finance, and sourcing, as well as in the medical and news domains. These case studies show notable enhancements in both efficiency and accuracy. Technical obstacles, such as dataset diversity, model scalability, and ethical considerations like bias mitigation and factual accuracy, are carefully analyzed. Prospective research avenues are suggested to augment the functionalities and applications of long-context LLMs, establishing them as pivotal tools for transforming information processing across diverse sectors and enterprise applications.

This study presents a novel approach to enhance Large Language Models (LLMs) like Alpaca by dynamically integrating real-time information. This method addresses the issue of content hallucination and data relevancy by automatically collecting and integrating current data from credible sources into model prompts. Experiments show a significant improvement in accuracy and a decrease in content hallucination, with a manageable increase in response time. The research underscores the potential of real-time data integration in making LLMs more accurate and contextually relevant, setting a foundation for future advancements in dynamic data processing in AI.

The scope of a lucrative career promoted by Google through its video distribution platform YouTube 1 has attracted a large number of users to become content creators. An important aspect of this line of work is the feedback received in the form of comments which show how well the content is being received by the audience. However, volume of comments coupled with spam and limited tools for comment classification makes it virtually impossible for a creator to go through each and every comment and gather constructive feedback. Automatic classification of comments is a challenge even for established classification models, since comments are often of variable lengths riddled with slang, symbols and abbreviations. This is a greater challenge where comments are multilingual as the messages are often rife with the respective vernacular. In this work, we have evaluated top-performing classification models and four different vectorizers, for classifying comments which are a mix of different combinations of English and Malayalam (only English, only Malayalam and Mix of English and Malayalam). The statistical analysis of results indicates that Multinomial Naïve Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest and Decision Trees offer similar level of accuracy in comment classification. Further, we have also evaluated 3 multilingual sub-types of the novel NLP language model, BERT and compared its’ performance to the conventional machine learning classification techniques. XLM was the top-performing BERT model with an accuracy of 67.31%. Random Forest with Term Frequency Vectorizer was the best the top-performing model out of all the traditional classification models with an accuracy of 63.59%.

: Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) using images that portray point distributions on a two-dimensional plane. We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these combinatorial challenges. Our experimental investigation includes rigorous evaluations across zero-shot settings and introduces innovative multi-agent zero-shot in-context scenarios. The re-sults demonstrated that both multi-agent models—Multi-Agent 1, which includes the Initializer, Critic, and Scorer agents, and Multi-Agent 2, which comprises only the Initializer and Critic agents—significantly improved solution quality for TSP and mTSP problems. Multi-Agent 1 ex-celled in environments requiring detailed route refinement and evaluation, providing a robust framework for sophisticated optimizations. In contrast, Multi-Agent 2, focusing on iterative re-finements by the Initializer and Critic, proved effective for rapid decision-making scenarios. These experiments yield promising outcomes, showcasing the robust visual reasoning capabilities of MLLMs in addressing diverse combinatorial problems. The findings underscore the potential of MLLMs as powerful tools in computational optimization, offering insights that could inspire further advancements in this promising field.

The classification of goods involved in international trade in Brazil is based on the Mercosur Common Nomenclature (NCM). The classification of these goods represents a real challenge due to the complexity involved in assigning the correct category codes especially considering the legal and fiscal implications of misclassification. This work focuses on the training of a classifier based on Bidirectional En-coder Representations from Transformers (BERT) for the tax classification of goods with NCM codes. In particular, this article presents results from using a specific Portuguese Language tuned BERT model as well results from using a Multilingual BERT. Experimental results justify the use of these models in the classification process and also that the language specific model has a slightly better performance.

This research investigates the potential application of generative language models, especially ChatGPT, in aviation safety analysis as a means to enhance the efficiency of safety analyses and accelerate the time it takes to process incident reports. In particular, ChatGPT was leveraged to generate incident synopses from narratives, which were subsequently compared with ground truth synopses from the Aviation Safety Reporting System (ASRS) dataset. The comparison was facilitated by using embeddings from Large Language Models (LLMs), with aeroBERT demonstrating the highest similarity due to its aerospace-specific fine-tuning. A positive correlation was observed between synopsis length and their cosine similarity. In a subsequent phase, human factor issues involved in incidents as identified by ChatGPT were compared to human factor issues identified by safety analysts. A concurrence rate of 61% was found, with ChatGPT demonstrating a cautious approach towards attributing human factor issues. Finally, the model was used to attribute incidents to relevant parties. As no dedicated ground truth column existed for this task, a manual evaluation was conducted. ChatGPT attributed the majority of incidents to the Flight Crew, ATC, Ground Personnel, and Maintenance. This study opens new avenues for leveraging AI in aviation safety analysis.

The high demand for liquefied natural gas (LNG) requires more LNG carriers (LNGCs) to be in operation. During transportation, there is a high risk due to the required extremely low temperatures and the explosive nature of LNG cargo. Moreover, when there is a lack of experience in operating old LNGCs, there is a serious concern regarding operational accidents. A systematic maintenance strategy, especially for LNG cargo containment systems, is crucial for maintaining safe LNG transportation at sea. The purpose of this study is to develop preventive LNG cargo containment system maintenance models by using LNGC dock specifications from LNGCs of various ages. The dock specifications from a conventional LNGC repairing dock were analyzed using natural language processing techniques in order to develop preventive maintenance models of the LNG cargo containment system. From these results, and by considering the ship’s age, it was found that for young LNGCs the priority for repair should focus on checking routine consumable spare parts by tank inspections, whereas for older LNGCs the focus should be on tank condition maintenance rather than on other facilities. These results are expected to be useful in the development of a maintenance strategy of preventive LNG cargo containment systems in maritime LNG transportation.

Recommender Systems (RecSys) are crucial in managing information overload and enhancing user satisfaction across various digital platforms, including e-commerce and entertainment. Evolving from traditional models to Deep Neural Networks (DNNs) and, more recently, Large Language Models (LLMs), these systems leverage sophisticated algorithms to analyze user behaviors and preferences. LLMs, such as GPT-4, are trained on extensive datasets to comprehend and generate natural language, significantly advancing their ability to deliver personalized recommendations. This tutorial explores the transformative impact of LLMs on RecSys, discussing their development, application in handling complex datasets, and the integration of contextual insights. Real-world examples illustrate how LLMs enhance recommendation accuracy and user experience, highlighting challenges and future directions in the field.

Tactics, Techniques, and Procedures (TTPs) constitute the most valuable aspect of Cyber Threat Intelligence (CTI). However, TTPs are often implicit in unstructured text, necessitating manual analysis by field experts. Automating the classification of TTPs from unstructured text is a crucial task in contemporary research. MITRE ATT&CK serves as the de facto standard for studying TTPs. Existing research constructs classification datasets based on its procedural examples for tactics and techniques. However, due to a significant proportion of small sample categories, a long-tail phenomenon exists, leading to a highly imbalanced sample distribution. Consequently, more research concentrates on categories with relatively abundant samples. This paper proposes a method that combines ChatGPT data augmentation with Instruction Supervised Fine-Tuning of open large language models. This approach offers a solution for TTPs classification in few-shot learning scenarios, achieving coverage of 625 technical categories. The Precision, Recall, and F1 scores reach 86.2%, 89.9%, and 87.3%, respectively.

The accurate diagnosis and effective treatment of mental health disorders such as depression remain challenging owing to the complex underlying causes and varied symptomatology. Traditional information extraction methods struggle to adapt to evolving diagnostic criteria such as the Diagnostic and Statistical Manual of Mental Disorders fifth edition (DSM-5) and to contextualize rich patient data effectively. This study proposes a novel approach for enhancing information extraction from mental health data by integrating medical knowledge graphs and large language models (LLMs). Our method leverages the structured organization of knowledge graphs specifically designed for the rich domain of mental health combined with the powerful predictive capabilities and zero-shot learning abilities of LLMs. This research enhances the quality of knowledge graphs through entity linking and demonstrates superiority over traditional information extraction techniques, making a significant contribution to the field of mental health. It enables a more fine-grained analysis of the data and the development of new applications. Our approach redefines the manner in which mental health data are extracted and utilized. By integrating these insights with existing healthcare applications, the groundwork is laid for the development of real-time patient monitoring systems. The performance evaluation of this knowledge graph highlights its effectiveness and reliability, indicating significant advancements in automating medical data processing and depression management.

The development of intelligent medical service robots for patient care presents significant chal-lenges, particularly in integrating diverse knowledge sources and enabling robots to autono-mously perform tasks in dynamic and unpredictable healthcare environments. This study in-troduces a novel framework that combines large language models (LLMs) with healthcare-specific knowledge and robotic operations to enhance autonomous task execution for a Robotic Health Attendant (RHA). Utilizing OpenAI’s ChatGPT, the RHA processes structured information about patient care protocols and unstructured human inputs to generate context-aware robot actions. A prototype system was tested in a simulated patient room where the RHA successfully performed both simple individual actions and complex tasks involving the execution of multiple actions, based on real-time dialogues with the LLM and predefined task specifications. The results demonstrate the potential of LLMs to reduce the reliance on hardcoded logic and provide healthcare professionals with the ability to interact with robotic systems through natural lan-guage.

Estimating Visual Quality of Street Space (VQoSS) is pivotal for urban design, environmental sustainability, civic engagement, etc. Recent advancements, notably in deep learning, have enabled large-scale analysis. However, traditional deep learning approaches are hampered by extensive data annotation requirements and limited adaptability across diverse VQoSS tasks. Multimodal Large Language Models (MLLMs) have recently demonstrated proficiency in various computer vision tasks, positioning them as promising tools for automated VQoSS assessment. In this paper, we pioneer the application of MLLMs to VQoSS change estimation, with our empirical findings affirming their effectiveness. In addition, we introduce Street Quality GPT (SQ-GPT), a model that distills knowledge from the current most powerful but inaccessible (not free) GPT-4, requiring no human efforts. SQ-GPT approaches GPT-4’s performance and is viable for large-scale VQoSS change estimation. In a case study of Nanjin, we showcase the practicality of SQ-GPT and knowledge distillation pipeline. Our work promises to be a valuable asset for future urban studies research.

Artificial intelligence (AI) driven language models have seen a rapid rise in development, deployment, and adoption over the last few years. This surge has sparked many discussions about their societal and political impact, including political bias. Bias is a crucial topic in the context of large models due to its far-reaching consequences on technology, politics, and society. It significantly influences public perception, decision-making, political discourse, and AI policy governance and ethics. This study investigates political bias through a comparative analysis of four prominent AI models: ChatGPT-4, Perplexity, Google Gemini, and Claude.Through a comprehensive analysis by systematically and categorically evaluating their responses to politically and ideologically charged tests and prompts, utilizing the Pew Research Center’s Political Typology Quiz, the Political Compass assessment, and ISideWith political party quiz, this study identifies significant ideological leanings and the nature of political bias within these models. The findings revealed that ChatGPT-4 and Claude exhibit a liberal bias, Perplexity is more conservative, while Google Gemini adopts more centrist stances. The presence of such biases underscores the critical need for transparency in AI development and the incorporation of diverse training datasets, regular audits, and user education to mitigate these biases. This analysis also advocates for more robust practices and comprehensive frameworks to assess and reduce political bias in AI, ensuring these technologies contribute positively to society and support informed, balanced, and inclusive public discourse, which will point towards neutrality.The results of this study add to the ongoing discourse about the ethical implications and development of AI models, highlighting the critical need to build trust and integrity in AI models. Additionally, future research directions have been outlined to explore and address the complex issue of bias in AI.

(1) Background: Information overload challenges decision-making in the Industry 4.0 era. While Natural Language Processing (NLP), especially Automatic Text Summarization (ATS), offers solutions, issues with factual accuracy persist. This research bridges cognitive neuroscience and NLP, aiming to improve model interpretability. (2) Methods: This research examined four fact extraction techniques: dependency relation, named entity recognition, part-of-speech tagging, and TF-IDF, in order to explore their correlation with human EEG signals. Representational Similarity Analysis (RSA) was applied to gauge the relationship between language models and brain activity. (3) Results: Named entity recognition showed the highest sensitivity to EEG signals, marking the most significant differentiation between factual and non-factual words with a score of -0.99. The dependency relation followed with -0.90, while part-of-speech tagging and TF-IDF resulted in 0.07 and -0.52, respectively. Deep language models such as GloVe, BERT, and GPT-2 exhibited noticeable influences on RSA scores, highlighting the nuanced interplay between brain activity and these models. (4) Conclusions: Our findings emphasize the crucial role of named entity recognition and dependency relations in fact extraction and demonstrate the independent effects of different models and TOIs on RSA scores. These insights aim to refine algorithms to reflect human text processing better, thereby enhancing ATS models’ factual integrity.

Virtual assistants (VAs) have gained widespread popularity across a wide range of applications, and the integration of Large Language Models (LLMs) such as ChatGPT has opened up new possibilities for developing even more sophisticated VAs. However, this integration poses new ethical issues and challenges that must be carefully considered, particularly as these systems are increasingly used in public services: transfer of personal data, decision-making transparency, potential biases, and privacy risks. This paper, an extension of the work presented at IberSPEECH 2022, analyzes the current regulatory framework for AI-based VAs in Europe and delves into ethical issues in depth, examining potential benefits and drawbacks of integrating LLMs with VAs. Based on the analysis, this paper argues that the development and use of VAs powered by LLMs should be guided by a set of ethical principles that prioritize transparency, fairness, and harm prevention. The paper presents specific guidelines for the ethical use and development of this technology, including recommendations for data privacy, bias mitigation, and user control. By implementing these guidelines, the potential benefits of VAs powered by LLMs can be fully realized while minimizing the risks of harm and ensuring that ethical considerations are at the forefront of the development process.

Disaster issue consultation is crucial for effective emergency management, requiring timely and accurate information to support decision-making processes. This paper explores the integration of large language models (LLMs) with advanced prompt engineering to enhance the performance of AI systems in disaster management. We propose a novel multi-round prompt engineering approach that guides LLMs to iteratively refine their responses based on evolving disaster scenarios. Our method leverages diverse disaster-related datasets and employs a combination of accuracy metrics and a customized GPT-4 scoring system for evaluation. We conduct comprehensive experiments across multiple LLM platforms, including Qwen2, ChatGPT, Claude, and GPT-4, comparing our approach with baseline models and the Tree of Thoughts (ToT) method. The results demonstrate significant improvements in both accuracy and response quality, highlighting the effectiveness of our method in providing contextually relevant and actionable insights. Additional analysis confirms the robustness and generalizability of our approach across various disaster scenarios, establishing it as a valuable tool for enhancing disaster management practices.

The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes ArabianGPT, a series of transformer-based models within the ArabianLLM suite designed explicitly for Arabic. These models, including ArabianGPT-0.1B and ArabianGPT-0.3B, vary in size and complexity, aligning with the nuanced linguistic characteristics of Arabic. The AraNizer tokenizer, integral to these models, addresses the unique morphological aspects of Arabic script, ensuring more accurate text processing. Empirical results from fine-tuning the models on tasks like sentiment analysis and summarization demonstrate significant improvements. For sentiment analysis, the fine-tuned ArabianGPT-0.1B model achieved a remarkable accuracy of 95%, a substantial increase from the base model's 56%. Similarly, in summarization tasks, fine-tuned models showed enhanced F1 scores, indicating improved precision and recall in generating concise summaries. Comparative analysis of fine-tuned ArabianGPT models against their base versions across various benchmarks reveals nuanced differences in performance, with fine-tuning positively impacting specific tasks like question answering and summarization. These findings underscore the efficacy of fine-tuning in aligning ArabianGPT models more closely with specific NLP tasks, highlighting the potential of tailored transformer architectures in advancing Arabic NLP.

Decision-making is a complex process of selecting an option from the given choices by analyzing the background information like risk, loss, and gain within the alternative options presented. It has been observed in earlier studies that people are prompt to make less rational decisions when choices are given in a language less known to them. Therefore, to understand the effect of languages on decision-making, we have questioned native Hindi speakers in French and English. French being the foreign language, and English as their second language. Thus, this effect of a non-native language brings to light the important role that the native language plays routinely in judgment and decision-making. In this paper, we developed a Neuropsychological assessment to decipher the effects on decision-making between choices when given in foreign language and second language in comparison with the native language of an individual, which is termed as foreign language effect(Fle). We have explored various possible situations to understand the foreign language effect(Fle) in decision-making and does this change translates when the decision is to be made in the second language. Our study concludes that the Foreign language is least affected by the intuitive biases, followed by the second language, and the native language is most affected by it.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

Programming languages drive most if not all of modern problem- solving using computational methods and power. Research into new programming languages and methods is essential to the furthering or improvement of computational problem-solving by making the design, implementation, and application of automation to general or particu- lar problem-solving ever easier, more accessible, and more performant. General-purpose Programming Languages (GPLs) typically are designed to be purely domain agnostic—meaning they can be applied in any field, for any kind of problem. However, this typically also makes them hard and difficult to apply in problems where non-programmers or even ex- perts with little or no GPL programming skills are required to leverage programmatic problem solving capabilities, which is why Domain Specific Languages (DSLs) come into play; they are generally more fine-tuned to- wards improving human productivity and performance than that of the machine, while making solving particular, domain-oriented problems sim- pler. In this paper, we review the literature concerning how to design and then fully implement a new DSL, with special focus on a DSL for generic problem-solving leveraging Text Processing methods—essentially, a Text Processing Language (TPL). We consider leveraging the design research paradigm and philosophy as a systematic framework for guiding research into the development of new TPLs. This work presents for the first time, new unifying theory concerning general, but also TPL-specific language engineering theory and guiding frameworks—UPLT, PLEF & PLEf. We consider quantitative but also qualitative evaluation of programming lan- guages. The SOE framework is re-introduced for this purpose too. Finally, we set the pace for future theoretical and practical research into the field of programming language engineering especially with focus on TPLs.

Sign Language Recognition (SLR) aims to bridge speech-impaired and general communities by recognizing signs from given videos. Researchers still face challenges developing efficient SLR systems because of the video’s complex background, light illumination, and subject structures. Recently many researchers developed a skeleton-based sign language recognition system to overcome the subject and background variation of hand gesture signs. However, skeleton-based SLR is still under exploration due to the lack of information and annotations on hand key points. More recently, researchers included body and face information with the hand gesture for the SLR, but their performance and efficiency are unsatisfactory. We proposed a Multi-Stream Graph-based Deep Neural Network (SL-GDN) for a skeleton-based SLR system to overcome the problems. The main purpose of the proposed SL-GDN approach is to improve the efficiency and performance of the SLR system with a low computational cost based on the human body pose in the form of 2D landmark locations. In the procedure, firstly, we constructed a skeleton graph based on the selected 27 whole-body key points among 67 key points to solve the inefficiency problems. Then we proposed multi-stream SL-GDN to extract features from the whole-body skeleton graph for four streams. Finally, we concatenated the four different features and applied a classification module to refine the feature and recognize corresponding sign classes. Our data-driven and graph construction method increases the system’s flexibility and brings high generability to adapt various data samples. We used three large-scale benchmark SLR datasets to evaluate the proposed model: WLASL, AUTSL and CSL. The demonstrated performance accuracy table proved the superiority of the proposed model, and we believe this will be considered a great invention in the SLR domain.

The development of language and communication patterns has been significantly impacted by the internet's quick advancement. The ability to instantly communicate globally and engage with people of different linguistic origins is one of the main advantages of using the internet. Internet use has significant positive effects on language growth, but it also brings with it drawbacks that need to be addressed. Online communication's casual atmosphere can occasionally cause grammar norms to deteriorate and non-standard language patterns to proliferate. With the information stated in this paper, the aim now is to collect literature on the benefits of internet usage and the evolution of language to provide substantive information in regard to this matter. In order to assist students in navigating the complexity of Internet communication, educational institutions should incorporate digital literacy into their curricula. This involves upholding strict requirements for traditional language proficiency while teaching students how to use digital technologies efficiently. The Internet should be used to support the revitalization and preservation of endangered languages. This can entail setting up community forums, digital archives, and online learning portals where language users can interact and exchange resources.

Natural language processing model (NLP) are used in chatbots to understand user input, interpret its meaning, and generate conversational responses to provide immediate and consistent assistance. This reduces problem-solving time and staff workload and increases user satisfaction. There are both rule-based chatbots, which use decision trees and are programmed to answer specific questions, and self-learning chatbots, which can handle more complex conversations through continuous learning about data and user interactions. However, only a few chatbots have been developed specifically for the Italian language. This work proposes an NLP model to develop a powerful and efficient Italian QA (Question Answering) chatbot that is easy to use for Italian Public Administration (PA). The proposed model is based on BERT (Bidirectional Encoder Representations from Transformer) architecture, where an Encoder/Decoder module and a Highway Network module have been added to perform more efficient filtering of input text. The Italian version of the Stanford Question Answering Dataset (SQuAD-IT) is used to test the proposed model. The proposed model is one of the first models developed for Italian language-specific chatbots.

This critical review delves into the often-overlooked aspect of early childhood language development: the potential impact of exposure to foreign languages. While multilingualism is widely celebrated for its cognitive and cultural benefits, emerging research suggests that early exposure to foreign languages may pose challenges for young children's linguistic development. The review synthesizes findings from 17 studies to explore the complexities surrounding this issue, including linguistic confusion, language delay, reduced vocabulary growth, impaired language processing, and socio-emotional implications. Additionally, mitigating factors and future directions for research and intervention are discussed. By shedding light on this topic, the review aims to inform educators, parents, and policymakers about the nuances of bilingual language acquisition and the importance of providing tailored support to optimize early childhood language development in multilingual contexts.

This review paper investigates the influence of gestures on foreign language (FL) vocabulary learning through a series of experiments conducted in our laboratory. The manipulation of the gesture-word relationship was a consistent factor across the studies. Firstly, we examined the impact of gestures on noun and verb learning. The results revealed that participants exhibited better learning outcomes when FL words were accompanied by congruent gestures compared to a no gesture condition. This suggests that gestures have a positive effect on FL learning when there is a meaningful connection between the words and the accompanying gestures. However, in general, the recall of words in conditions where gestures were incongruent or lacked meaning was lower than in the no gesture condition. This indicates that under certain circumstances, gestures may have a detrimental impact on FL learning. We analyzed these findings in terms of their implications for facilitating or interfering with FL acquisition. Secondly, we addressed the question of whether individuals need to physically perform the gestures themselves to observe the effects of gestures on vocabulary learning. To explore this, participants were divided into two experimental groups. In one group, participants learned the words by actively performing the gestures ("do" learning group), while the other group simply observed the gestures performed by others ("see" learning group). The processing of congruent gestures facilitated the recall of FL words in both the "see" and "do" learning groups. However, the interference effect associated with processing incongruent gestures was more pronounced in the "see" learning group than in the "do" learning group. Thus, the performance of gestures appears to mitigate the negative impact that gestures may have on the acquisition of FL vocabulary. In conclusion, our findings suggest that iconic gestures can serve as an effective tool for learning vocabulary in a FL, particularly when the gestures align with the meaning of the words. Furthermore, the active performance of gestures helps counteract the negative effects associated with inconsistencies between gestures and word meanings. Consequently, if a choice must be made, a FL learning strategy in which learners acquire words while making gestures congruent with their meaning would be highly desirable.

Stop words are very important for information retrieval and text analysis investigation. This study aimed to automatically analyze and detect stop words in texts in the Uzbek language. Because of the limited availability of methods for automatic search of stop words of texts in Uzbek we analyzed a newly prepared corpus. The Uzbek language belongs to the family of agglutinative languages. As with all agglutinative languages, we can explain that the detection of stop words in Uzbek texts is a more complex process than in inflected languages: In inflected languages, words such as auxiliary words, articles, prepositions can be included in the stop words group. In agglutinative languages, the meanings of such words are hidden in the text. Therefore, it is not appropriate to apply all known methods of stop words detection in inflected languages directly to agglutinative languages. In this work, the “School corpus” which contains 731156 Uzbek words has been investigated. The bigram method of analysis was applied to the corpus. We proposed the collocation method of detecting stop words of the corpus. We proposed the method of automatically detecting stop words of texts in Uzbek. It is shown that the collocation method is 6 times better than the bigram method.

Arabic is present in the Arab world and beyond. It is used as an official (or co-official) language in the Arab World (this refers to the twenty-two member states of the Arab League). Also, Arabic has the status of a national language in Mali, Niger, and Senegal. Besides, it is spoken in linguistic enclaves in Nigeria, Cyprus, Turkey, Uzbekistan, Iran, and Afghanistan. In addition, it is employed as the liturgical language in Muslim countries and countries with a Muslim minority all over Africa and Asia. As a result of the migration to Western countries since the end of the nineteenth century, Arabs and Arabic has been present in such countries. The presence of Arabs in Western countries raises the following question: Are these Arabs language maintainers or language shifters? The present article is an attempt to answer this question through reviewing a number of studies that have dealt with Arabic language maintenance among the Arabs living in Western countries (namely the United States of America, the United Kingdom, Canada, Australia, New Zealand, Sweden, Greece, and France), deducing from these studies the major trends in Arabic language maintenance among these Arabs, and providing a critique of the studies.

Hallyu or the Korean wave has sweeped through nations especially the Philippines. This exploratory study offers a dip into the effects of the Hallyu wave on a Filipino speaker through ambient exposure, consequently on the development of a Korean proto-lexicon through indirect vocabulary acquisition. Finally, a focus group discussion and a preliminary assessment tested out the waters of the effects of Hallyu on casual Filipino speakers. A thorough statistically comprehensive qualitative study on the acquisition framework is recommended to provide substantial evidence to support the framework.

This study explores the integration of Building Information Modelling (BIM) and Virtual Tours in the Architecture Engineering and Construction (AEC) industry, focusing on Facility Management (FM) and Computerized Maintenance Management Systems (CMMS). The research addresses the need for different levels of detail in BIMs across various building phases and the potential of Virtual Tours as a complement to BIMs in IoT-based FM. The study’s methodology includes a literature review, a pilot-demonstrator case study, installation of monitoring and IoT control devices, execution of BIMs and Virtual Tour models, and development of links between system elements. The case study is based on the Controlled Environments for Living Lab Studies (CELLS), a unique facility designed for flexible monitoring and remote-control processes. The findings of this research could provide valuable insights into the potential of Virtual Tours to complement and connect to BIMs within a life cycle perspective, enhancing the usability of digital twins for nontrained users and contributing to the evolution of the AEC industry.

The era of digital technology has brought about a substantial shift in language development, especially for younger generations who have grown up surrounded by it. Language development is impacted by digital media exposure in both positive and bad ways. Positively, users can interact with a variety of linguistic communities across the globe by using digital platforms, which offer a wealth of options for linguistic exposure and practice. This exposure can promote imaginative language use, increase vocabulary, and improve reading comprehension. Since the brevity and informality of digital communication frequently stress speed over correctness, there are worries that digital media could encourage shallow communication, shorter attention spans, and a deterioration in professional writing skills. This paper aims to gather literature about language development in the digital age. In order to make sure that technical breakthroughs support language development, standards for the responsible and balanced use of digital media in educational settings must also be developed. Teachers can better support their students' language development in a constantly changing digital environment by remaining knowledgeable and flexible.

Securing funding is a critical yet complex task for organizations and individuals. This study presents an innovative chatbot designed to streamline the process using advanced Natural Language Processing (NLP) techniques and, specifically, a Retrieval-Augmented Generation (RAG) pipeline optimized for real-world applications. Our chatbot assists users in identifying suitable public tenders for financial support through natural language queries and a comprehensive public data database. The chatbot operates in a two-stage interaction model, initially providing summarized tender information for exploratory brainstorming, followed by detailed data upon user selection. A custom filtering mechanism ensures that the user interface elements responsible for swapping the interaction stages are consistent with the responses generated by the conversational agent. Human-evaluation tests demonstrated an average accuracy of 90.4% in document retrieval, with an average of 2.11 interactions required to find a specific tender. User satisfaction, rated on a scale of 1 to 5, averaged 3.14 (±1.73), indicating generally positive user experience with room for improvement. This approach addresses challenges of relevance, accuracy, and conversational flow, resulting in a reliable chatbot that simplifies the process of finding funding opportunities.

In an era marked by rapid technological progress and global dynamics, the Neo-Language Acquisition and Learning Theory challenges conventional language acquisition paradigms through its conceptualization of 'Grit: The Unyielding Will to Connect,' emphasizing determination, motivation, and adaptability as the primary drivers of language learning, transcending age-related constraints and critical periods. This theory also underscores 'Self-Preservation: Language as the Canvas of Reality,' as language plays a pivotal role in preserving and conveying our individual and collective experiences. Recent global events have underscored the theory's relevance, prompting a reevaluation of language education in response to changing circumstances. Moreover, 'Techno-Training: Language Acquisition and Learning in the Digital Age' is integral to the theory, as it recognizes the influence of technology on modern language education. Beyond traditional methods, these three reshape our fundamental understanding of said theory. Drawing from historical evidence, psychological principles, and contemporary applications, they supported the conceptualization of the theory itself. Overall, the Neo-Language Acquisition and Learning Theory revolutionizes language education, spotlighting the power of motivation, determination, and adaptability to navigate the evolving landscape of language learning and acquisition.

This systematic review examines the potential of digital language learning in contributing to students' cognitive gains. The study reviews existing research on the relationship between digital language learning and cognitive benefits, with a focus on enhanced problem-solving skills, memory, and multitasking ability. The findings indicate that higher levels of digital competences correlate positively with language proficiency outcomes, suggesting that participants with greater digital skills achieve better language learning outcomes. Digital technologies offer interactive and engaging methods of learning, which can positively impact retention and understanding. However, the study also acknowledges the limitations of digital foreign language learning, such as the lack of face-to-face interaction and the need for high motivation and discipline. The research questions explored in this study are: (1) Does digital language learning contribute to cognitive gains in foreign language education? and (2) What are the pedagogical implications for cognitive improvement in digital foreign language education? The study employs the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) methodology to identify and analyze relevant research articles. The results of the review suggest that working with printed texts may be more effective for cognitive gains compared to electronic texts. Additionally, implementing more senses through digital language education appears to be beneficial for cognitive gains. The article concludes by discussing the implications of these findings and the need for further research in this area.

There is a serious concern regarding framing rules and guidelines to regulate the content on OTT platforms that needs urgent attention. In the Current Scenario, the use of vulgar language in the public domain on OTT platforms needs to take seriously. Some OTT platforms heavenly use foul language, which is open to children that cause a huge psychological impact on them. The use of vulgar language, including profanity and bad words, has to be regulated strictly. Web series uses obscene, abusive words and foul language with excessive usage. This review paper highlights the excessive use of swear words, profane language, and vulgar expletives on OTT platforms.

This study provides a detailed examination of Natural Language Processing (NLP) for the complexscript of Nepali. We analyze available data resources today and discuss relevant points includingcharacter encoding, advanced tokenization methods and morphological complexity. This allows us tocontrast Nepal’s unique language and technology ecosystem with Hindi and Thai in terms of NLPadvancements. Quantitative assessment of existing tools and resources is offered by this investigationwhich highlights immediate weaknesses as well as areas that need more effort. Various ethicalconcerns are addressed here while potential topics for future research as e-governance, healthcare oreducation with a focus on new domain-specific applications, and cross-lingual transfer learning aresuggested. The objective of this attempt is to enhance understanding of natural language processing(NLP) in Nepali language and beyond aimed at developing NLP technologies that are more efficient,inclusive, culturally appropriate across diverse linguistic communities.

In an era where the proliferation of large language models blurs the lines between human and machine-generated content, discerning text authenticity is paramount. This study investigates transformer-based language models—BERT, RoBERTa, and DistilBERT—in distinguishing human-written from machine-generated text. By leveraging a comprehensive corpus, including human-written text from sources such as Wikipedia, WikiHow, various news articles in different languages, and texts generated by OpenAI's GPT-2, we conduct rigorous comparative experiments. Our findings highlight the superior effectiveness of ensemble learning models over single classifiers in this critical task. This research underscores the versatility and efficacy of transformer-based methodologies for a wide range of natural language processing applications, significantly advancing text authenticity detection systems. The results demonstrate competitive performance, with the transformer-based method achieving an F-score score of 0.83 with RoBERTa-large (monolingual) and 0.70 with DistilBERT-base-uncased (multilingual).

In this review paper, we discuss the use of BERT, one of the most well-liked deep learning-based language models. The model's operation mechanism, key areas of applicability to text analytics tasks, comparisons with related models for each activity, and a description of certain proprietary models are all covered in this work. The data from several dozen original scientific studies that have been published in the last few years and have garnered the greatest interest from the scientific community were systematized in order to prepare this review. All researchers and students who wish to learn about the most recent developments in the field of natural language text analysis may find this survey helpful. Bidirectional Encoder Representations from Transformers, or BERT for short, is the subject of a thorough investigation that we present. The area of natural language processing holds significant importance in the creation of intelligent systems. To do a variety of activities, one must comprehend the sentence's correct meaning in order to produce the desired result. Computers have a hard time understanding languages because of how context constantly changes. The main challenge in natural language processing tasks is getting computers to understand text context, and BERT is seen as a revolution in this regard. It picks up the language and its meaning in a manner that is quite similar to how the human brain processes meaning from sentences. Its capacity to identify a word from both the left and right contexts of a sentence makes it special. A new era in the perception and comprehension of natural languages has been ushered in with the development of BERT, which could help computers understand natural languages more fully. This study aims to provide readers with a deeper knowledge of the BERT language model and how it is applied to different NLP tasks.

(1) Background: Attention Deficit Hyperactivity Disorder (ADHD) and Developmental Language Disorder (DLD) are neurodevelopmental disorders that affect various areas of chil-dren’s development, such as language. There is an emerging idea that ADHD is characterised by the presence of language difficulties, which could be explained by the high comorbidity between ADHD and DLD. The purpose of this study is to analyse the empirical evidence of language com-petence in children aged 6–17 years old, diagnosed with ADHD and/or DLD. (2) Method: Fifteen studies with experimental designs were identified from Scopus, PsycINFO and WoS databases, reporting on language skills in children diagnosed with ADHD and/or DLD. Studies relating ex-ecutive functioning to language skills in this target population were also included. (3) Results: The literature is heterogeneous and different components of language are also examined. Even though the results are contradictory they convincingly demonstrate that there are overlapping symptoms between ADHD and DLD, such as language skills and executive functions. (4) Conclusions: the differences in the samples limit the generalisability of the results. Therefore, this review highlights the importance of considering language skills when designing individualised interventions for the population with ADHD and DLD, both in comorbidity and in isolation.

while enjoying a relative positive revival in the digital age, Esperanto and the assessment of its language vitality is often problematic and prone to gross errors, and therefore a theoretical re-flection is required. Unlike other lesser-used languages, Esperanto is intergenerationally trans-mitted mainly outside the family, and so Fishman’s GIDS and subsequent scales such as the EGIDS cannot be applied straightforwardly for language vitality diagnosis and estimation. In particular, it is the social movement with its language activists who guarantee its vitality and developing, for more than a century. A key aspect is the digital domain, where the relatively good positioning of Esperanto does not reflect in a parallel increase in the number of activists. This paper critically assesses the digital language vitality of Esperanto on the basis of its language ide-ology and other sociolinguistic data as a starting point for a discussion to overcome the limits of Blanke’s (2006) scale of language vitality of Esperanto and its rivals. This assessment eventually leads to a more general reflection on the role of ‘coolification’, i.e., the positive effects on language attitudes and development thanks to digital visibility, its limits and the issue of placing it in the context of language vitality in general.

Despite the growing capabilities of large language models, concerns exist about the biases they develop. In this paper, we propose a novel, automated mechanism for debiasing through specified dataset augmentation in the lens of bias producers that can be useful in a variety of industries, especially ones that are “restricted” and have limited data. We consider that bias can occur due to intrinsic model architecture and dataset quality. The two aspects are evaluated using two different metrics we created. We show that our dataset augmentation algorithm reduces bias as measured by our metrics.

The advancement of agricultural technology is intrinsically linked to the evolution of the agricultural industry, with the latter being contingent upon technological progress for its sustained enhancement. In the context of China, a nation of significant agricultural stature, the globalization of agricultural science and technology (Agri-Sci-Tech) has emerged as a pivotal narrative within the country's agricultural growth trajectory. The strategic alignment of China's Agri-Sci-Tech industry with its global counterparts is driven by the ambition to assimilate sophisticated agricultural production techniques and managerial acumen from its Western counterparts, thereby catalyzing the international expansion of the nation's Agri-Sci-Tech endeavors. This scholarly discourse delves into the imperative of interdisciplinary convergence, underscoring the paradigm and intrinsic attributes associated with the cultivation of agricultural expertise. It scrutinizes the prevailing state of foreign language instruction within the academic curriculum, positing strategic interventions and recommendations for the development of a robust agricultural foreign language talent cultivation framework. The treatise accentuates the criticality of cultivating a multifaceted agricultural talent pool proficient in foreign languages, advocating for a "professional+foreign language" model that facilitates international dialog within China's Agri-Sci-Tech industry and bolsters the creation of globally recognized brands. Moreover, the cultivation of a "foreign language+professional" composite talent model is posited as a transformative solution to the existing impasse in foreign language education in China, offering a novel pathway for educational innovation and global competitiveness within the agricultural domain.

The rapid advancement of technology has revolutionized language learning, introducing innovative methods that depart from traditional instructional approaches. This study employs a mixed-methods research design to examine the impact of chatbot-based language learning support, adaptive learning algorithms, and virtual reality language immersion on the language learning proficiency and self-regulated learning skills of English as a Foreign Language (EFL) learners. The research design includes quantitative analysis of language proficiency scores and qualitative exploration of learner experiences with the technological interventions. The theoretical implications of this study are rooted in constructivist and socio-cultural learning theories, which underpin the design and implementation of the technological interventions. The triangulation of qualitative and quantitative data revealed that the participants' positive perceptions of the effectiveness of chatbot-based language learning support were supported by the quantitative results, with the variable "chat-bot based support" demonstrating a substantial mean difference compared to other groups. This convergence of findings reinforces the positive influence of chatbot-based support on language learning outcomes and highlights the importance of integrating theoretical perspectives with empirical evidence to gain a comprehensive understanding of the impact of technological interventions on language learning outcomes for EFL learners. The study's findings provide insights into the potential of these technological interventions to optimize language learning outcomes for EFL learners and promote autonomous learning behaviors.

As large language models (LLMs) continue to advance, evaluating their comprehensive capabilities becomes significant for their application in various fields. This research study comprehensively evaluates the language, vision, speech, and multimodal capabilities of GPT-4o. The study employs standardized exam questions, reasoning tasks, and translation assessments to assess the model's language capability. Additionally, GPT-4o's vision and speech capabilities are tested through image classification and object recognition tasks, as well as accent classification. The multimodal evaluation assesses the model's performance in integrating visual and linguistic data. Our findings reveal that GPT-4o demonstrates high accuracy and efficiency across multiple domains in language and reasoning capabilities, excelling in tasks that require few-shot learning. GPT-4o also provides notable improvements in multimodal tasks compared to its predecessors. However, the model shows variability and faces limitations in handling complex and ambiguous inputs, particularly in audio and vision capabilities. This paper highlights the need for more comprehensive benchmarks and robust evaluation frameworks, encompassing qualitative assessments involving human judgment as well as error analysis. Future work should focus on expanding datasets, investigating prompt-based assessment, and enhancing few-shot learning techniques to test the model's practical applicability and performance in real-world scenarios.

Sustainable development and education in sustainable development (ESD) are crucial and interconnected topics under wide discussion today. Young adults need to be educated in how to help bring about change. Thus, the dynamic relationship between school and home is important. In education, use could be made of English language classes, especially since English is a global language that enables access to the sustainability literature and facilitates discussion in global conferences and meetings. Consequently, English as a foreign language (EFL) students could gain confidence from being able to understand and use the terminology of, for example, sustainability. In this paper, the use of competence-based language teaching (CBLT) is proposed as a means of introducing sustainability topics into EFL writing classes at a university in Saudi Arabia. Students’ competence in sustainable development is therefore considered based on their ability to write about suggested sustainable development topics, measured on a scale for five dimensions of ESD proposed by Michelsen and Fischer (2017). The results demonstrate that the students possessed competence in sustainable development and intended to participate in its implementation. Thus, recommendations are made for the stakeholders in the education sector to include sustainable development topics as an initial offering in the curricula of various specialties using the CBLT approach.

Natural language processing (NLP) is being widely used globally for a variety of value-creation tasks ranging from chat-bots and machine translations to sentiment and topic analysis and multilingual large language models (LLMs). However, most of the advances are initially implemented within the English language framework, and it takes time and resources to develop comparable resources in other languages. The advances in machine translations have enabled the rapid and effective conversion of content in global languages into English and vice-versa. This creates potential opportunities to apply English language NLP methods and tools to other languages via machine translations. However, although this idea is powerful, it needs to be validated and processes and best practices need to be developed and kept updated. The present research is an effort to contribute to the development of best practices and an evaluation framework. We present a systematic and repeatable state-of-the-art process to evaluate the viability of applying English language sentiment analysis tools to Italian text by using multiple English language machine translation mechanisms such that it can be easily extended to other languages. hor[RU,RA]{\large Richard Anderson} \address[RU]{\large Rutgers University, USA} \address[RA]{\large rick.anderson@rutgers.edu} \author[RU]{\large Carmela Scala} \author[RU]{\large Jim Samuel} \author[UC]{\large Vivek Kumar} \address[UC]{\large University of Cagliari, Italy} \author[RU]{\large Parth Jain}

Large Language Models (LLMs) have revolutionized the field of Artificial Intelligence with their ability to understand and generate natural language discourse. This has led to the use of LLMs in various creative fields such as music, art, and storytelling, which has sparked a debate on the impact of LLMs on human creativity. This article explores the cyclic effect of LLMs on human creativity, where LLMs can generate an ever-evolving cycle of creative output from both humans and machines. The article also highlights the importance of responsible and ethical use of LLMs, including privacy and copyright issues with the training data used by LLMs. The article emphasizes the need for transparency, data security measures, and AI governance policies to protect user data and ensure the safe use of LLMs. It also calls for the development of educational materials and resources to increase public understanding of LLMs and their ethical implications. The article concludes by highlighting the potential of LLMs as powerful tools for communication and education, but also emphasizes the need for ethical considerations to ensure the responsible and beneficial use of LLMs in society.

Micro-level language policy and planning (LPP) primarily concerns local actors' decision-making on matters in relation to language(s) and its users. Despite a growing body of literature focusing on micro language planning in educational settings, there is a scarcity of research examining early childhood education settings such as micro-level LPP context for young English language learners. By adopting a case study approach, the present study examined the educators' enactment of agency in micro-planning the English language education policy (LEP) in one Chinese kindergarten and the associated factors shaping their agency. Our study revealed that the sustainable implementation of the kindergarten English LEP depended on the principal, native English-speaking teachers, and the Chinese assistant teachers' different degrees of agency. Also, the research findings indicated an array of contextual and individual factors nested in a hierarchical structure that facilitated, guided, and constrained the educators' agency in a role-and circumstance-dependent manner. This study contributes to the pertinent literature by casting nuanced light on the different educators' contributions to the micro-level LPP against a national policy that does not endorse early-year English language education.

Paraphrase Generation is one of the most important and challenging tasks in the field of Natural Language Generation. The paraphrasing techniques help to identify or to extract/generate phrases/sentences conveying the similar meaning. The paraphrasing task can be bifurcated into two sub-tasks namely, Paraphrase Identification (PI) and Paraphrase Generation (PG). Most of the existing proposed state-of-the-art systems have the potential to solve only one problem at a time. This paper proposes a light-weight unified model that can simultaneously classify whether given pair of sentences are paraphrases of each other and the model can also generate multiple paraphrases given an input sentence. Paraphrase Generation module aims to generate fluent and semantically similar paraphrases and the Paraphrase Identification systemaims to classify whether sentences pair are paraphrases of each other or not. The proposed approach uses an amalgamation of data sampling or data variety with a granular fine-tuned Text-To-Text Transfer Transformer (T5) model. This paper proposes a unified approach which aims to solve the problems of Paraphrase Identification and generation by using carefully selected data-points and a fine-tuned T5 model. The highlight of this study is that the same light-weight model trained by keeping the objective of Paraphrase Generation can also be used for solving the Paraphrase Identification task. Hence, the proposed system is light-weight in terms of the model’s size along with the data used to train the model which facilitates the quick learning of the model without having to compromise with the results. The proposed system is then evaluated against the popular evaluation metrics like BLEU (BiLingual Evaluation Understudy):, ROUGE (Recall-Oriented Understudy for Gisting Evaluation), METEOR, WER (Word Error Rate), and GLEU (Google-BLEU) for Paraphrase Generation and classification metrics like accuracy, precision, recall and F1-score for Paraphrase Identification system. The proposed model achieves state-of-the-art results on both the tasks of Paraphrase Identification and paraphrase Generation.

The purpose of this systematic review is to provide second language acquisition (SLA) researchers with an overview of research trends in this field in the last ten years (2009-2019). In doing so, three international peer-reviewed journals, Studies in Second Language Acquisition, Language Teaching Research, and The Modern Language Journal, were selected. 150 articles were systematically selected and analyzed. The analysis of data resulted in identifying six descriptive themes. Results showed that some areas of second language acquisition still need further exploration while some areas are of great interest for researchers. Some suggestions for future research as well as implications of the study were discussed in detail.

This study explores advanced feature engineering and semantic enrichment methods to enhance text classification, focusing on detecting figurative language in tweets. The novel features introduced, Syno\_Lower\_Mean and Syn\_Mean, measure the use of uncommon synonyms and the mean frequency of synonyms, capturing semantic richness crucial for detecting figurative expressions. Using resources like SenticNet and Framester, we enrich our feature set with sentiment and frame semantic information. Our approach includes extensive data preprocessing, sophisticated feature selection, and implementing various classification models, such as SVM, KNN, Logistic Regression, Decision Trees, Random Forest, BERT, and LSTM networks. We rigorously evaluate each model's performance to assess the effectiveness of our features and enrichment methods. Putting emphasis on model explainability, we use decision tree analysis, feature importance analysis, and the TREPAN algorithm to approximate SVM decisions. Although we focus on figurative language detection, our methods have broader implications for various NLP text classification tasks. Our findings demonstrate significant improvements in classification accuracy and interpretability through innovative feature design and dataset enrichment.

Purpose. This article examines the use of English medium instruction (EMI) for teaching Japanese as a foreign language (JFL) by non-native speakers with a focus on multilingual classrooms. The study also explores teachers’ positive and negative beliefs about using EMI in classroom settings for JFL instruction.Methods and procedure. Two hundred sixty-one non-native Japanese language teachers worldwide voluntarily participated in the survey, answering the questionnaire (Google Forms and Jotforms) used to gather data. Both qualitative and quantitative methods were employed. The research instrument was piloted before the main study and was found to be effective and adequate to elicit the desired data. The research questions aimed to identify whether there were any relationships between the use of EMI and the multilingual classroom. Findings. The results showed a clear correlation between the extensive use of EMI and the multilingual character of JFL multilingual classrooms. Translanguaging turned out to be a common practice adopted by non-native Japanese teachers regardless of the primary language of instruction. The article concludes that EMI can be a valuable tool for JFL instruction in multilingual classrooms. Based on the investigation of the teachers’ beliefs, the study results showed a changing positive attitude towards English employed in JFL classrooms. Implications for research and practice. The findings can be used further to investigate EMI in JFL instructional practices in multilingual classrooms, to improve the quality of JFL instruction, and to facilitate the integration of multilingual education into foreign language teaching. Future research can explore the effectiveness of EMI in different JFL contexts and investigate the impact of EMI on students’ language learning outcomes.

According to a recent study by OpenAI, Open Research, and the University of Pennsylvania, large language models (LLMs) based on artificial intelligence (AI), such as Generative Pretrained Transformers (GPTs), may have potential implications on the job market, specifically regarding job occupations that demand writing or programming skills. The research points out Interpreters and Translators as one of the main job occupations with greater exposure to AI in the US job market (76.5%). This article, following a mixed-methods survey-based research, provides insights into the Portuguese Language Service Providers (LSPs) awareness and knowledge about AI, specifically regarding neural machine translation (NMT) and large language models (LLM), its actual use and usefulness, as well as their potential influence on work performance and labour market. The results show that most professionals are unable to identify if AI and/or automation technologies support the tools that are most used in the profession. The usefulness of AI is essentially low to moderate and the professionals who are less familiar with it and less knowledgeable also demonstrate lack of trust in it. Two thirds of the sample estimate negative or very negative effects of AI in the profession, expressing as main concerns the devaluation and replacement of experts, the reduction of income, and the reconfiguration of the career of translator to mere post-editors.

The dominance of social media has added to the channels of bullying to perpetrators. Unfortunately, cyberbullying (CB) is the most prevalent phenomenon in today’s cyber world and is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms to manage the impact in our society. Several machine learning (ML) algorithms have been proposed for this purpose. However, their performances are not consistent due to high class imbalance issue and generalisation. In recent years, large language models (LLM) like BERT and RoBERTa have achieved state of the art (SOTA) results in several natural language processing (NLP) tasks. Unfortunately, the LLMs have not been applied extensively. In our paper, we explored the use of these models for cyberbullying (CB) detection. We have prepared a new dataset (D2) from existing studies (Formspring and Twitter). Our experimental results for dataset D1 and D2 showed RoBERTa outperformed other models.

This paper addresses the grammatical challenges associated with the development of clause complexity, focusing on the performance of a group of monolingual Spanish-speaking schoolchildren with Specific Language Impairment/Developmental Language Disorder (SLI/DLD) in a longitudinal corpus of oral narrative samples. The study examines the presence of interclause relations of subordination and equivalence (hypotaxis and parataxis) in language samples of two groups: an experimental group made up of 24 schoolchildren with SLI/DLD and a control group made up of 24 schoolchildren with typical development (TD). The results show that while both groups use parataxis as the most common relation between clauses in all school grades, there is a significant decrease in paratactic relations and a significant increase in hypotactic relations from first to fourth grade of primary education. Although the development patterns are highly similar, the SLI/DLD group shows greater difficulties in mastering more complex (hypotactic) relations in fourth grade compared to the control group, indicating that they are less sophisticated in the use of these types of complex relations. These findings suggest that focused support on the most complex structures is needed towards the fourth grade of primary education, given the demands of the school academic register from 6 and 7 years of age, and the potential problems that the development of clause complexity can cause in school-age children.

Large language model (LLM) is a representation of a major advancement in AI, and has been used in multiple natural language processing tasks. Nevertheless, in different business scenarios, LLM requires fine-tuning by engineers to achieve satisfactory performance, and the cost of achieving target performance and fine-tuning may not match. Based on the Baidu STI dataset, we study the upper bound of the performance that classical information retrieval methods can achieve under a specific business, and compare it with the cost and performance of the participating team based on LLM. This paper gives an insight into the potential of classical computational linguistics algorithms, and which can help decision-makers make reasonable choices for LLM and low-cost methods in business R&D.

The advent of Large Language Models (LLMs) has significantly advanced natural language processing (NLP), yet their application to historical texts remains challenging due to archaic language, distinct terminologies, and varied contextual backgrounds. This study introduces Historical Domain Large Language Models, designed to bridge this gap by adapting LLMs for better comprehension and processing of historical data. Our approach leverages context-aware and task-specific prompts to enhance model performance in tasks such as named entity recognition (NER), sentiment analysis, and information extraction within historical contexts. We propose an iterative refinement process to improve prompt quality and model outputs continuously. Instruction tuning on newly collected evaluation data ensures our methods' efficacy, avoiding biases from previously used datasets. Evaluations using GPT-4 demonstrate significant improvements in handling historical texts, underscoring the potential of our approach to unlock profound insights from historical data. This work highlights the importance of tailored LLM adaptations for specialized domains, offering a robust framework for future research in historical NLP.

This study evaluates the ability of six popular chatbots; ChatGPT-3.5, ChatGPT-4.0, Gemini, Copilot, Chatsonic, and Perplexity to provide reliable answers to questions concerning keratoconus. Methods: Chatbots responses were assessed using mDISCERN and Global Quality Score (GQS) metrics. Readability was evaluated using nine validated readability assessments. We also addressed the quality and accountability of websites from which the questions originated. Results: We analyzed 20 websites, 65% "Private practice or independent user" and 35% "Official patient education materials." The mean JAMA Benchmark score was 1.5±0.68, indicating low accountability. Reliability, measured using mDISCERN, ranged from 42.9±3.16 (ChatGPT-3.5) to 46.95±3.53 (Copilot). The most frequent question was "What is Keratoconus?" with 70% of websites providing relevant information. This received the highest mDISCERN score (49.33±4.96) and a relatively high GQS score (3.50±0.55), with an Automated Readability Level Calculator score of 13.17±2.13. Moderate positive correlations were determined between the website numbers and both mDISCERN (?=0.265,?=0.25) and GQS (?=0.453,?=0.05) scores. The quality of information, assessed using the GQS, ranged from 3.01±0.51 (ChatGPT-3.5) to 3.3±0.65 (Gemini) (p=0.34). The differences between the texts were statistically significant. Gemini emerged as the easiest to read, while ChatGPT-3.5 and Perplexity were the most difficult. Based on mDISCERN scores, Gemini and Copilot exhibited the highest percentage of responses in the "Good" range (51-62 points). For the GQS, the Gemini model exhibited the highest percentage of responses in the "Good" quality range, with 40% of its responses scoring 4-5. Conclusions: While all chatbots performed well, Gemini and Copilot showed better reliability and quality. However, their readability often exceeded recommended levels. Continuous improvements are essential to match information with patients' health literacy for effective use in ophthalmology.

RNA sequencing techniques, like bulk RNA-seq and Single Cell (sc) RNA-seq, are critical tools for the biologist looking to analyze the genetic activity/transcriptome of a tissue or cell during an experimental procedure. Platforms like Illumina's next-generation sequencing (NGS) are used to produce the raw data for this experimental procedure. This raw FASTQ data must then be prepared via a complex series of data manipulations by bioinformaticians. This process currently takes place on an unwieldy textual user interface like a terminal/command line that requires the user to install and import multiple program packages, preventing the untrained biologist from initiating data analysis. Open-source platforms like Galaxy have produced a more user-friendly pipeline, yet the visual interface remains cluttered and highly technical, remaining uninviting for the natural scientist. To address this, SeqMate is a user-friendly tool that allows for one-click analytics by utilizing the power of a large language model (LLM) to automate both data preparation and analysis (differential expression, trajectory analysis, etc). Furthermore, by utilizing the power of generative AI, SeqMate is also capable of analyzing such findings and producing written reports of upregulated/downregulated/user-prompted genes with sources cited from known repositories like PubMed, PDB, and Uniprot.

In this paper, we introduce Syntax-Enhanced Transformer Model (SET), a groundbreaking approach in the realm of Transformer-based language modeling that seeks to redefine the boundaries of linguistic analysis and comprehension. SET innovatively combine (i) the well-established high-level performance, scalability, and adaptability of traditional Transformers with (ii) a sophisticated analysis of syntactic structures. This synergy is enabled by a novel attention mechanism tailored to parse syntactic nuances and a deterministic process adept at transforming linearized parse trees into meaningful linguistic representations. Our comprehensive experiments reveal that SET significantly advance the field by surpassing existing benchmarks in sentence-level language modeling perplexity. They exhibit exceptional proficiency in tasks that require an acute awareness of syntax, setting new standards for language models in understanding complex linguistic structures. Furthermore, SET demonstrate an enhanced capability to grasp nuanced linguistic patterns that have traditionally been challenging for standard Transformer models. However, our studies also uncover a unique aspect of SET: while they excel in sentence-level tasks, their representation of sentences as singular vectors—owing to the syntactic composition constraints intrinsic to their design—introduces certain limitations in document-level language modeling. This observation points to an intriguing area for future exploration; it suggests the potential need for an alternative or complementary memory mechanism within Transformer models, one that functions independently from, yet in harmony with, syntactic structures. Such a mechanism could be pivotal in enhancing the model's ability to comprehend and process long-form texts effectively. In conclusion, SET mark a significant stride in the journey towards more sophisticated, syntax-aware language models. They offer promising insights into the integration of deep linguistic knowledge with cutting-edge machine learning techniques, potentially opening doors to a new era of natural language understanding and processing.