arXiv 2409.100112024-09-18cs.CLcs.AI

HALO：幻觉分析与学习优化，为引导临床决策赋予大语言模型检索增强上下文

HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making

University of North Texas（北德克萨斯大学）；University of Tennessee（田纳西大学）；University of Tennessee Health Science Center（田纳西大学健康科学中心）

Sumera Anjum, Hanzhi Zhang, Wenjun Zhou, Eun Jin Paek, Xiaopeng Zhao, Yunhe Feng

备注：: 10 pages, 4 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出HALO框架，通过查询变体生成、外部知识检索和最大边际相关性排序来减少医学问答中的幻觉，显著提升了Llama-3.1和ChatGPT的准确性，改善临床决策。

摘要：

大语言模型（LLMs）显著推进了自然语言处理任务，但它们容易生成不准确或不可靠的响应，这种现象被称为幻觉。在健康与医学等关键领域，这些幻觉可能带来严重风险。本文介绍了HALO，一个新颖的框架，旨在通过聚焦于幻觉的检测与缓解，提升医学问答（QA）系统的准确性和可靠性。我们的方法利用LLMs生成给定查询的多个变体，并从外部开放知识库中检索相关信息以丰富上下文。我们采用最大边际相关性评分来优先排序检索到的上下文，然后将其提供给LLMs进行答案生成，从而降低幻觉风险。LangChain的集成进一步简化了这一过程，使得开源和商业LLMs（如Llama-3.1（从44%提升至65%）和ChatGPT（从56%提升至70%））的准确性显著且稳健地提升。该框架强调了在医学QA系统中解决幻觉问题的关键重要性，最终改善临床决策和患者护理。开源的HALO可在以下网址获取：https://github.com/ResponsibleAILab/HALO。

英文摘要：

Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health and medicine, these hallucinations can pose serious risks. This paper introduces HALO, a novel framework designed to enhance the accuracy and reliability of medical question-answering (QA) systems by focusing on the detection and mitigation of hallucinations. Our approach generates multiple variations of a given query using LLMs and retrieves relevant information from external open knowledge bases to enrich the context. We utilize maximum marginal relevance scoring to prioritize the retrieved context, which is then provided to LLMs for answer generation, thereby reducing the risk of hallucinations. The integration of LangChain further streamlines this process, resulting in a notable and robust increase in the accuracy of both open-source and commercial LLMs, such as Llama-3.1 (from 44% to 65%) and ChatGPT (from 56% to 70%). This framework underscores the critical importance of addressing hallucinations in medical QA systems, ultimately improving clinical decision-making and patient care. The open-source HALO is available at: https://github.com/ResponsibleAILab/HALO.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。