Article
Version 1
Preserved in Portico This version is not peer-reviewed
Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI
Version 1
: Received: 24 October 2023 / Approved: 24 October 2023 / Online: 26 October 2023 (03:37:39 CEST)
How to cite: Ahmad, M.; Yaramic, I.; Roy, T. D. Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI. Preprints 2023, 2023101662. https://doi.org/10.20944/preprints202310.1662.v1 Ahmad, M.; Yaramic, I.; Roy, T. D. Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI. Preprints 2023, 2023101662. https://doi.org/10.20944/preprints202310.1662.v1
Abstract
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.
Keywords
LLM; AI hallucination; ChatGPT
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment