Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks, but their deployment comes at a high computational and financial cost. On the other hand, smaller language models (SLMs), which can be deployed on lower-cost edge devices, struggle to match the performance of their larger counterparts. This paper presents a novel hybrid inference approach that leverages the strengths of both model types while minimizing reliance on costly cloud-based LLMs. Unlike existing methods that route entire queries to either an SLM or a cloud LLM, our approach introduces a reward-based mechanism to dynamically determine the involvement of the cloud LLM during token generation. Specifically, each token predicted by the SLM is evaluated against a reward score, and only when this score falls below a certain threshold is the cloud LLM consulted for assistance in the next token prediction. This method not only reduces the traffic to the cloud LLM, thereby lowering costs, but also allows for flexible control over response quality depending on the reward score threshold. Experimental results demonstrate that our approach significantly reduces cloud LLM usage with minimal impact on overall response quality, offering a cost-effective solution for deploying high-performance language models.

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.

The rapid advancement of large language models (LLMs), such as ChatGPT, has revolutionized natural language processing, enabling these models to generate coherent and contextually relevant text. These capabilities hold significant potential for various applications, particularly in the medical field. LLMs can assist healthcare professionals by providing accurate information, supporting diagnostic processes, and enhancing medical education. However, the implementation of LLMs in clinical settings faces several barriers, including technical limitations, ethical concerns, regulatory constraints, and practical challenges. Ensuring accuracy, reliability, and interpretability is crucial, along with addressing biases, ensuring data privacy, and establishing ethical guidelines. Future research should focus on improving training techniques, developing explainable AI methods, and creating efficient, resource-saving models. Expanding applications through domain-specific models and multi-modal integration can further unlock the potential of LLMs. By addressing these challenges and prioritizing responsible development, LLM technology can be safely and effectively integrated into various domains, driving innovation and improving outcomes. This paper explores the current state of LLM technology, its medical applications, barriers to implementation, and directions for future research and development

Large language models have proliferated across multiple domains in as short period of time. There is however hesitation in the medical and healthcare domain towards their adoption because of issues like factuality, coherence, and hallucinations. Give the high stakes nature of healthcare, many researchers have even cautioned against its usage until these issues are resolved. The key to the implementation and deployment of LLMs in healthcare is to make these models trustworthy, transparent (as much possible) and explainable. In this paper we describe the key elements in creating reliable, trustworthy, and unbiased models as a necessary condition for their adoption in healthcare. Specifically we focus on the quantification, validation, and mitigation of hallucinations in the context in healthcare. Lastly, we discuss how the future of LLMs in healthcare may look like.

The Mixture of Experts (MoE) architecture has evolved as a powerful and versatile approach for improving the performance and efficiency of deep learning models. This survey aims to provide the fundamental principles of MoE in details, a paradigm that harnesses the collective power of multiple specialized "expert" models working in concert to tackle complex tasks.Our exploration is a thorough analysis of the core components that constitute the MoE framework. We begin by dissecting the routing mechanism, a crucial element responsible for dynamically assigning input data to the most appropriate expert models. This routing process is pivotal in ensuring that each expert's specialized knowledge is optimally utilized. The survey places significant emphasis on expert specialization, a key feature that sets MoE apart from traditional architectures. We examine various strategies for developing and training specialized experts, exploring how this specialization enables MoE models to effectively handle diverse and multifaceted problems.Load balancing, another critical aspect of MoE systems, receives thorough attention. We discuss techniques for efficiently distributing computational resources among experts, ensuring optimal model performance while managing hardware constraints. This section provides insights into the delicate balance between model capacity and computational efficiency. Furthermore, we provide an in-depth discussion of the expert models themselves, examining their architectural designs, training methodologies, and how they interact within the larger MoE framework. This includes an analysis of different types of experts, from simple neural networks to more complex, task-specific architectures. The survey also navigates through diverse research avenues within the MoE landscape, highlighting recent advancements and innovative applications across various domains of machine learning. We pay particular attention to the burgeoning use of MoE in two rapidly evolving fields: computer vision and large language model (LLM) scaling. By providing this comprehensive overview, our survey aims to offer researchers and practitioners a deep understanding of MoE's capabilities, current applications, and potential future directions in the ever-evolving landscape of deep learning.The Mixture of Experts (MoE) architecture has evolved as a powerful and versatile approach for improving the performance and efficiency of deep learning models. This survey aims to provide the fundamental principles of MoE in details, a paradigm that harnesses the collective power of multiple specialized "expert" models working in concert to tackle complex tasks.Our exploration is a thorough analysis of the core components that constitute the MoE framework. We begin by dissecting the routing mechanism, a crucial element responsible for dynamically assigning input data to the most appropriate expert models. This routing process is pivotal in ensuring that each expert's specialized knowledge is optimally utilized. The survey places significant emphasis on expert specialization, a key feature that sets MoE apart from traditional architectures. We examine various strategies for developing and training specialized experts, exploring how this specialization enables MoE models to effectively handle diverse and multifaceted problems.Load balancing, another critical aspect of MoE systems, receives thorough attention. We discuss techniques for efficiently distributing computational resources among experts, ensuring optimal model performance while managing hardware constraints. This section provides insights into the delicate balance between model capacity and computational efficiency. Furthermore, we provide an in-depth discussion of the expert models themselves, examining their architectural designs, training methodologies, and how they interact within the larger MoE framework. This includes an analysis of different types of experts, from simple neural networks to more complex, task-specific architectures. The survey also navigates through diverse research avenues within the MoE landscape, highlighting recent advancements and innovative applications across various domains of machine learning. We pay particular attention to the burgeoning use of MoE in two rapidly evolving fields: computer vision and large language model (LLM) scaling. By providing this comprehensive overview, our survey aims to offer researchers and practitioners a deep understanding of MoE's capabilities, current applications, and potential future directions in the ever-evolving landscape of deep learning.

Intellecta dataset emerges as an innovative synthetic dataset, engineered to enhance the cognitive processing capabilities of contemporary language models. With a composition of 11.53 billion tokens, integrating 8.01 billion tokens of synthetic data with 3.52 billion tokens of rich textbook data, Intellecta is crafted to foster advanced reasoning and comprehensive educational narrative generation. Leveraging the Mixtral-8x7B-Instruct-v0.1 model, the dataset facilitates the generation of complex thought processes and detailed, textbook-style explanations, thus enabling language models to engage in both critical thinking and profound educational discourse. This hybrid dataset stands as a testament to the potential of synthetic data in pushing the boundaries of AI, offering a repository that is not only vast and varied but also refined to align with ethical standards and intellectual rigor.

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies’ environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% (1252 W for A100 with AMD EPYC 7V13 vs 613 W for Intel® Xeon® Gold 6538N) while providing production ready throughput & latency.

With the rapid advancement of Artificial Intelligence (AI), ensuring ethical safeguards is paramount, especially for powerful Large Language Models (LLMs). This paper delves into the challenges and implications of AI's transformative potential, particularly the risks associated with the generation of harmful content. A comprehensive review of existing ethical guidelines and risk assessment strategies is provided, highlighting notable efforts like the Asilomar AI Principles and the IEEE Ethically Aligned Design guidelines. The novel concept of "indelible ethical frameworks" is introduced, emphasizing the embedding of ethical constructs deep within AI systems to make them resistant to tampering. A critical analysis of this approach is presented, acknowledging its potential while addressing its challenges. The paper also explores the intricacies of ethically programming LLMs, emphasizing the significance of prompt engineering and the handling of unusual prompts. Through a series of witty exposés, the ethical journey of language models is narrated, likening their programming challenges to real-world ethical dilemmas. The piece concludes with proposed methodologies for researching AI safeguards, advocating for both reverse engineering complemented by ethical hacking and longitudinal monitoring with audit trails. These methodologies aim to reinforce the ethical integrity of AI systems, ensuring they are beneficial, transparent, and aligned with societal values..

GPT-4 was released in March 2023 to wide acclaim, marking a very substantial improvement across the board over GPT-3.5 (OpenAI's previously best model, which had powered the initial release of ChatGPT). Despite the genuinely impressive improvement, however, there are good reasons to be highly skeptical of GPT-4's ability to reason. This position paper discusses the nature of reasoning; criticizes the current formulation of reasoning problems in the NLP community and the way in which the reasoning performance of LLMs is currently evaluated; introduces a collection of 21 diverse reasoning problems; and performs a detailed qualitative analysis of GPT-4's performance on these problems. Based on the results of this analysis, the paper argues that, despite the occasional flashes of analytical brilliance, GPT-4 at present is utterly incapable of reasoning.

The launch of Open AI's chatbot, ChatGPT, has generated a lot of attention and discussion among professionals in several fields. Many concerns and challenges have been brought up by researchers from various fields, particularly in relation to the harm that using these tools for medical diagnosis and treatment recommendations can cause. Additionally, it has been debated if ChatGPT is dependable, efficient, and helpful for clinicians and medical professionals. Therefore, in this study, we assess ChatGPT's effectiveness in providing mental health support, particularly for issues related to anxiety and depression, based on the chatbot's responses and cross-questioning. The findings indicate that there are significant inconsistencies and that ChatGPT's reliability is low in this specific domain. As a result, care must be used when using ChatGPT as a complementary mental health resource.

Conventional tutoring approaches are confronted with limitations such as restricted availability, inconsistent pedagogical quality, and scalability con-straints. Furthermore, the exclusive use of Large Language Models (LLMs) like ChatGPT in education has its shortcomings, including the potential for incorrect responses and the lack of customized guidance aligned with specific course con-tent. This research proposes an innovative intelligent chatbot tutoring system, in-tegrating the Retrieval Augmented Generation (RAG) approach with a custom LLM. The developed system aims to overcome the limitations of traditional tu-toring and general-purpose LLMs by providing accurate, contextually relevant, and personalized assistance, thereby enhancing student understanding and en-gagement. The system, powered by an intelligent agent, retrieves relevant information from curated academic sources, incorporates interactive features for user feedback, and utilizes machine learning algorithms for ongoing performance enhancement, ensuring a robust and effective tutoring experience. The anticipated outcome is an enriched educational experience for university students, advance-ment in personalized learning, and improved student engagement, retention, and academic performance. Through continuous research and refinement, it is expected that the intelligent chatbot tutor will assume an important role in enhancing and supporting the educational journey of students.

LangChain is a rapidly emerging framework that offers a ver- satile and modular approach to developing applications powered by large language models (LLMs). By leveraging LangChain, developers can sim- plify complex stages of the application lifecycle—such as development, productionization, and deployment—making it easier to build scalable, stateful, and contextually aware applications. It provides tools for han- dling chat models, integrating retrieval-augmented generation (RAG), and offering secure API interactions. With LangChain, rapid deployment of sophisticated LLM solutions across diverse domains becomes feasible. However, despite its strengths, LangChain’s emphasis on modularity and integration introduces complexities and potential security concerns that warrant critical examination. This paper provides an in-depth analysis of LangChain’s architecture and core components, including LangGraph, LangServe, and LangSmith. We explore how the framework facilitates the development of LLM applications, discuss its applications across multi- ple domains, and critically evaluate its limitations in terms of usability, security, and scalability. By offering valuable insights into both the capa- bilities and challenges of LangChain, this paper serves as a key resource for developers and researchers interested in leveraging LangChain for innovative and secure LLM-powered applications.

Large language models (LLMs) get quickly implemented into question answering and support systems to automate customer experience across all domains even including medical use cases. Models in such environments should solve multiple problems like general knowledge questions, queries to external sources, function calling and many others. Some cases might not even require a full-on text generation. They possibly need different prompts or even models. All of it can be managed by a routing step. This paper focuses on interpretable few-shot approaches for conversation routing like latent embeddings retrieval. The work here presents a benchmark, a sorrow analysis, and a set of visualizations of the way latent embeddings routing works for long-context conversations in a multilingual, domain-specific environment. The results presented here show that latent embeddings router is able to achieve performance on the same level as LLM-based routers with additional interpretability and higher level of control over model decision making.

The continuous expansion of Large Language Models (LLMs) has significantly transformed the fields of artificial intelligence (AI) and natural language processing (NLP). This paper reviews the rapidly evolving domain of language models and introduces the concept of Extremely Large Language Models (XtremeLLMs), a new category defined for models exceeding one trillion parameters. These models are monumental in scale and engineered to enhance performance across a diverse range of language tasks. This study aims to establish a comprehensive framework that explores the significant opportunities and complex challenges presented by such extensive scaling and emphasises the implications for future advancements in the field.

I propose a test for machine self-awareness inspired by the Turing test. My test is simple, and it provides an objective, empirical metric to rectify the ungrounded speculation surging through industry, academia, and social media. Drawing from a breadth of philosophical literature, I argue the test captures the essence of self-awareness, rather than some postulated correlate or ancillary quality. To begin, the concept of self-awareness is clearly demarcated from related concepts like consciousness, agency, and free will. Next, I propose a model called the Nesting Doll of Self-Awareness and discuss its relevance for intelligent beings. Then, the test is presented in its full generality, applicable to any machine system. I show how to apply the test to Large Language Models and conduct experiments on popular open and closed source LLMs, obtaining reproducible results that suggest a lack of self-awareness. The implications of machine self-awareness are discussed in relation to questions about meaning and true understanding. Finally, some next steps are outlined for studying self-awareness in machines.

As modern technologies, particularly home assistant devices, become more integrated into our daily lives, they are also making their way into the domain of energy management within our homes. Homeowners, now acting as prosumers, have access to detailed information in 15-minute or even 5-minute intervals, including weather forecasts, outputs from Renewable Energy Sources (RES)-based systems, appliance schedules and the current energy balance, which details any deficits or surpluses along with their quantities and the predicted prices on the Local Energy Market (LEM). The goal for these prosumers is to reduce costs while ensuring their home’s comfort levels are maintained. However, given the complexity and the rapid decision-making required in managing this information, the need for a supportive system is evident. This is particularly true given the routine nature of these decisions, highlighting the potential for a system that provides personalized recommendations to optimize energy consumption, whether that involves adjusting the load or engaging in transactions with the LEM. In this context, we propose a recommendation system powered by Large Language Models (LLM), Scikit-llm and Zero-Shot Classifiers, designed to evaluate specific scenarios and offer tailored advice for prosumers based on the available data at any given moment. Two scenarios for a prosumer of 5.9 kW are assessed using candidate labels, such as Decrease, Increase, Sell and Buy.

On average, one in ten patients die because of a diagnostic error and medical errors are the third largest cause of death in the US. While LLMs have been proposed to help doctors with diagnoses, no research results have been published on comparing the diagnostic ability of many popular LLMs on an openly accessible real-patient cohort. In thus study, we compare LLMs from Google, OpenAI, Meta, Mistral, Cohere and Anthropic using our previously published evaluation methodology and explore improving their accuracy with RAG.

Single-cell RNA sequencing (scRNA-seq) technology has significantly advanced our understanding of the diversity of cells and how this diversity is implicated in diseases. Yet, translating these findings across various scRNA-seq datasets poses challenges due to technical variability and dataset-specific biases. To overcome this, we present a novel approach that employs both an LLM-based framework and explainable machine learning to facilitate generalization across single-cell datasets and identify gene signatures to capture disease-driven transcriptional changes. Our approach uses scBERT, which harnesses shared transcriptomic features among cell types to establish consistent cell-type annotations across multiple scRNA-seq datasets. Additionally, we employ a symbolic regression algorithm to pinpoint highly relevant yet minimally redundant models and features for inferring a cell type’s disease state based on its transcriptomic profile. We ascertain the versatility of these cell-specific gene signatures across datasets, showcasing their resilience as molecular markers to pinpoint and characterize disease-associated cell types. Validation is carried out using four publicly available scRNA-seq datasets from both healthy individuals and those suffering from ulcerative colitis (UC). This demonstrates our approach’s efficacy in bridging disparities specific to different datasets, fostering comparative analyses. Notably, the simplicity and symbolic nature of the retrieved gene signatures facilitate their interpretability, allowing us to elucidate underlying molecular disease mechanisms using these models.

Software systems are often maintained by a group of experienced software developers, in order to ensure that faults which may bring the system down are less likely. Large turnover in organizations such as CERN makes it important to think of ways of onboarding newcomers on a technical project rapidly. This paper focuses on optimizing the way that people get up-to-speed on the business logic and technologies used on the project, using a knowledge-imbued large language model that is enhanced using domain-specific knowledge from the group or team’s internal documentation.

This paper integrates carrier manifolds from control theory and hybrid systems modeling to develop a novel mathematical framework for Artificial General Intelligence (AGI). Carrier manifolds represent the state space of complex AGI systems, while hybrid systems model discrete and continuous dynamics together. The proposed architecture embeds carrier manifold into GPTProX, a hybrid AI solver combining conversational AI, logic programming, and optimization.

The article explores the concept of 'synthetic man' (SM) in the context of 'synthetic biology' (SB), analysing the potential, challenges, and ethical implications of these achievements. Through dialogue with ChatGPT 4, an in-depth understanding of the evolution, contributions of SM, ChatGPT's contribution, and concerns associated with SM is sought, providing insight into how this technology could affect our society. Our study uses a structured dialogue framework with ChatGPT that addresses essential SM questions regarding SM history, contributions, challenges, and concerns. ChatGPT responses are analysed to extract relevant information and identify trends and insights. The ChatGPT dialogue reveals that MS is still a theoretical and speculative concept with significant advances in gene therapy and genetic engineering. The potential contributions of SM in addressing global challenges such as health, environment and education are identified. Ethical and social concerns such as health risks and psychological impact are also highlighted. Differences in ChatGPT responses were observed between different sessions or even within the same session, which highlighted the limitations in the replicability of the research and sometimes the need for clarification of the questions. The article is distinguished by its unique approach of using an advanced language model to explore a complex and speculative topic. The LLM Dialogue Framework on Technology (LLM-DFonTech) framework proposal for structured dialogue with ChatGPT on various technological topics related to the original contribution provides an adaptable tool for interdisciplinary research in emerging technologies. This methodology opens up new possibilities for analyzing and developing trends in technology and society.

The electronic structural evolution of LLM-105 crystal and the (101) plane of LLM-105 crystal under different pressures is investigated by the density functional theory (DFT) calculations and the surface properties of seven low-Miller-index planes of LLM-105 crystal were investigated in this study. The result demonstrates that the surface energy of (101) plane of LLM-105 is much smaller when compared with other low-Miller-index planes of LLM-105.In order to further investigate the stability of crystal structure and (101) plane of LLM-105 under different pressures, a series of pressures ranged from 0 GPa to 55 GPa were applied during the DFT calculation, and the result shows that the electronic structures of LLM-105 crystal and the (101) plane changed with the increase of external pressure and the evolution process of (101) plane is different from that of LLM-105 crystal structure.

Modern language models are designed to generate text so realistic that it could easily be mistaken for human-authored content. Additionally, they can engage in conversations with humans in a manner that appears coherent and reasonable. The epitome of this technological advancement is ChatGPT, a model based on OpenAI's Generative Pretrained Transformer (GPT) language model. With its ability to produce high-quality content in mere seconds, ChatGPT surpasses other chatbots in terms of capabilities, drawing significant interest and excitement from both the business community and academic researchers. This study offers a comprehensive review of current research on ChatGPT, delving into its technological foundation, supportive mechanisms, and findings regarding its benefits across various fields and application areas. We evaluate and discuss the strengths and weaknesses of ChatGPT based on this review and suggest potential avenues for future research.

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.

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.

Visual thinking leverages spatial mechanisms in animals for navigation and reasoning. Therefore, given the challenge of abstract mathematics and logic, spatial reasoning-based teaching strategies can be highly effective. Our previous research verified that innovative box and ball coloring activities help teach elementary school students complex notions like quantifiers, logical connectors, and dynamic systems. However, given the richness of the activities, correction is slow, error-prone, and demands high attention and cognitive load from the teacher. Moreover, feedback to the teacher should be immediate. Thus, we propose to provide the teacher with real-time help with LLMs. We explored various prompting techniques with and without context Zero shot, Few shot, Chain of Thought, Visualization of Thought, Self Consistency, logicLM and Emotional to test GPT-4o’s visual, logical, and correction capabilities. We obtained that Visualization of Thought and Self Consistency techniques enabled GPT-4o to correctly evaluate 90% of logical-spatial problems that we tested. Additionally, we propose a novel prompt combining some of these techniques that achieved 100% accuracy on a testing sample, excelling in spatial problems and enhancing logical reasoning.

In the realm of mathematics education, self-explanation stands as a crucial learning mechanism, allowing learners to articulate their comprehension of intricate mathematical concepts and strategies. As digital learning platforms grow in prominence, there are mounting opportunities to collect and utilize mathematical self-explanations. However, these opportunities are met with challenges in automated evaluation. Automatic scoring of mathematical self-explanations is crucial for preprocessing tasks, including the categorization of learner responses, identification of common misconceptions, and the creation of tailored feedback and model solutions. Nevertheless, this task is hindered by the dearth of ample sample sets. Our research introduces a semi-supervised technique using the Language Learning Model (LLM), specifically its Japanese variant, to enrich datasets for the automated scoring of mathematical self-explanations. We rigorously evaluated the quality of self-explanations across five datasets, ranging from human-evaluated originals to ones devoid of original content. Our results show that combining LLM-based explanations with mathematical material significantly improves the model's accuracy. Interestingly, there's an optimal limit to how much synthetic self-explanation data can bene-fit the system. Exceeding this limit doesn't further improve outcomes. This study thus highlights the need for careful consideration when integrating synthetic data into solutions, especially within the mathematics discipline.

The primary cilium, the cell’s sensory and signaling antenna, is a dynamic cellular organelle during the cell cycle. It is resorbed before cells enter mitosis and reformed after cells exit mitosis, and as such acts as a structural barrier to mitosis. Cancer cells that undergo rapid cell cycle and replication have a low ciliation rate. Therefore, promoting cilia formation and elongation and thereby reducing their rates of retraction hold the key to blocking cell entry into mitosis and slowing down cancer cell replication. To perform a comprehensive and efficient literature search on drugs that can promote ciliogenesis, we developed an intelligent process that integrates the GPT-3.5 application programming interface (API) into a PubMed scraper that we coded, enabling the large language model (LLM) to directly query articles for predefined user questions. Among the top candidates identified are two FDA-approved drugs, Alvocidib and Alisertib, that showed strong potential to induce cilia formation and elongation. We first confirmed that these drugs can effectively increase the ciliation rate and the cilia length of DAOY medulloblastoma cells. We then applied Alvocidib and Alisertib individually or in combination to DAOY medulloblastoma and A549 lung cancer cells and observed a statistically significant decrease in the number of viable cells. These results demonstrated the potential of using cilia-promoting drugs to suppress cancer cell replication. Additionally, it shows the massive benefits of integrating accessible large language models to conduct sweeping, rapid, and accurate literature searches.

The disruptive application of ChatGPT (GPT-3.5, GPT-4) to a variety of domains has become a topic of much discussion in the scientific community and society at large. Large Language Models (LLMs), e.g., BERT, Bard, Generative Pre-trained Transformers (GPTs), LLaMA, etc., have the ability to take instructions, or prompts, from users and generate answers and solutions based on very large volumes of text-based training data. This paper assesses the impact and potential impact of ChatGPT on the field of digital forensics, specifically looking at its latest pre-trained LLM, GPT-4. A series of experiments are conducted to assess its capability across several digital forensic use cases including artefact understanding, evidence searching, code generation, anomaly detection, incident response, and education. Across these topics, its strengths and risks are outlined and a number of general conclusions are drawn. Overall this paper concludes that while there are some potential low-risk applications of ChatGPT within digital forensics, many are either unsuitable at present, since the evidence would need to be uploaded to the service, or they require sufficient knowledge of the topic being asked of the tool to identify incorrect assumptions, inaccuracies, and mistakes. However, to an appropriately knowledgeable user, it could act as a useful supporting tool in some circumstances.

ChatGPT, developed by OpenAI, is an advanced large language model (LLM) that leverages artificial intelligence (AI) and deep learning to generate human-like responses. This paper explores its applications in digital health and healthcare, focusing on enhancing patient engagement through medical history collection, symptom assessment, and decision support to improve diagnostic accuracy. We also examine its role in promoting health literacy and clinical decision-making across various organ systems. Despite its advantages, the integration of ChatGPT in healthcare poses limitations and risks, including the potential for inaccurate information, overreliance by users, and ethical concerns related to informed consent. We discuss the challenges of keeping pace with rapidly evolving medical knowledge and highlight the need for continuous updates. Additionally, the paper addresses intellectual property and regulatory issues associated with AI deployment in medicine. Through this analysis, we provide insights into the benefits and potential risks of employing ChatGPT in healthcare.

We present a novel benchmarking methodology for Large Language Models (LLMs) to evaluate their susceptibility to hallucinations, thereby determining their reliability for real-world applications involving greater responsibilities. This method, called Deception-Based Benchmarking, involves testing the model with a task that requires composing a short paragraph. Initially, the model performs under standard conditions. Then, it is required to begin with a misleading sentence. Based on these outputs, the model is assessed on three criteria: accuracy, susceptibility, and consistency. This approach can be integrated with existing benchmarks or applied to new ones, thus facilitating a comprehensive evaluation of models across multiple dimensions. It also encompasses various forms of hallucination. We applied this methodology to several small opensource models using a modified version of MMLU, DB-MMLU1 . Our findings indicate that most current models are not specifically designed to self-correct when the random sampling process leads them to produce inaccuracies. However, certain models, such as Solar-10.7B-Instruct, exhibit a reduced vulnerability to hallucination, as reflected by their susceptibility and consistency scores. These metrics are distinct from traditional benchmark scores. Our results align with TruthfulQA, a widely used benchmark for hallucination. Looking forward, DB-benchmarking can be readily applied to other benchmarks to monitor the advancement of LLMs.

Product attribute extraction is an growing field in e- commerce business, with several applications including product ranking, product recommendation, future assortment planning and improving online shopping customer experiences. Under- standing the customer needs is critical part of online business, specifically fashion products. Retailers uses assortment planning to determine the mix of products to offer in each store and channel, stay responsive to market dynamics and to manage inventory and catalogs. The goal is to offer the right styles, in the right sizes and colors, through the right channels. When shoppers find products that meet their needs and desires, they are more likely to return for future purchases, fostering customer loyalty. Product attributes are a key factor in assortment planning. In this paper we present PAE, a product attribute extraction algorithm for future trend reports consisting text and images in PDF format. Most existing methods focus on attribute extraction from titles or product descriptions or utilize visual information from existing product images. Compared to the prior works, our work focuses on attribute extraction from PDF files where upcoming fashion trends are explained. This work proposes a more comprehensive framework that fully utilizes the different modalities for attribute extraction and help retailers to plan the assortment in advance. Our contributions are three-fold: (a) We develop PAE, an efficient framework to extract attributes from unstructured data (text and images); (b) We provide catalog matching methodology based on BERT representations to discover the existing attributes using upcoming attribute values; (c) We conduct extensive experiments with several baselines and show that PAE is an effective, flexible and on par or superior (avg 92.5% F1-Score) framework to existing state-of-the-art for attribute value extraction task.

This paper represents a groundbreaking paradigm shift in network optimization. Departing from traditional static methodologies, this innovative approach harnesses the power of Generative Artificial Intelligence (AI) and Large Language Models (LLMs) to optimize cloud networks dynamically. By integrating advanced AI algorithms, this framework continuously adapts and evolves, ensuring optimal real-time performance. This dynamic optimization enhances efficiency and resilience, allowing cloud networks to adjust seamlessly to changing demands and conditions. Through the fusion of cutting-edge technology and adaptive intelligence, this approach heralds a new era in network optimization, empowering organizations to achieve unprecedent-ed levels of agility and scalability in their cloud infrastructures.

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.

In 2021, Japan's medical expenses will exceed 45 trillion yen, and the shortage of doctors, especially in remote and mountainous areas, is becoming serious, making it difficult to maintain the medical system. We have conducted a study of 800 health consultation text data. We developed an on-premise health counseling LLM system by constructing a dialogue flow based on 800 health counseling text data. We conducted a Turing test of this system using 200 test data and verified its effectiveness with three medical professionals. The Turing test was a comparison experiment between this system and a conventional LLM system. The health counseling LLM infrastructure focuses on exercise guidance and analyzes gender, height, weight, body fat percentage, and muscle mass. While the accuracy of the conventional LLM system was 87.5%, this system showed a higher accuracy of 93.1%. Although telemedicine has been slow to spread in Japan, the introduction of a health consultation system using Personal Health Record and Large Language Models has the potential to reduce the burden on physicians. In the future, we aim to improve the accuracy of the system by using Japanese language and medical-specific evaluation scales.

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.

Generative AI chatbots have emerged as a significant scientific contribution. They can produce text, images, audio, and video, and their applications are vast and varied in every field. However, it is identified that these chatbots can be used by script kiddies and malicious actors to generate phishing emails, security exploits, and executable payloads that can present notable risks and challenges for cybersecurity. This research provides an extensive review of the current status of the three most popular generative AI chatbots which are ChatGPT, Google Gemini, and Microsoft Bing. The article further reviews the different ways in which an attacker can intentionally use a chatbot for malicious activities and intensify cyber attacks. Moreover, the article provides insights on how an attacker uses certain keyword queries to manipulate chatbot behavior and tricks it into generating content that I won’t otherwise. We also explored the role of AI chatbots in enhancing cyber resilience against sophisticated attacks and their applications in detecting and mitigating security incidents. Finally, we proposed strategies that can empower modern chatbots to defend against such threats so that an attacker will not be able to bypass their content filtering mechanisms.

This paper presents MADS (Multi-Agents for Data Science), an innovative and simple open-source multi-agent framework designed for systemic pipeline execution in applied supervised machine learning. By leveraging the capabilities of multi-agent systems (MAS), we introduce a universal approach to optimize and streamline machine learning pipelines. Our framework highlights the differences between various types of agents, such as reinforcement learning (RL) agents and large language model (LLM) agents, and their distinct contributions to the process. While we currently employ LLM agents to automate and enhance machine learning tasks, we acknowledge the potential of incorporating RL agents in future iterations to further improve performance and adaptability. The primary objective is to enhance the efficiency, scalability, and adaptability of supervised learning applications across various domains. This integration addresses the complexity and manual effort typically associated with machine learning workflows, paving the way for more automated, robust, and scalable solutions. Our approach demonstrates significant improvements in task automation, reduced human intervention, and enhanced model performance. The MADS framework, which will soon be available as an open-source implementation, represents a pivotal contribution to the field of machine learning, promising to facilitate broader adoption and collaborative advancement.