用事实核查提升大模型医疗问答的准确性
LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models
- 通过事实核查优化检索生成流程，不更新参数
- 利用核查结果进行自训练，更新模型参数
- 适合医疗等对准确性要求高的场景
大语言模型在自然语言处理任务中表现卓越，但在医疗等知识密集型领域常出现事实错误。本文提出LEAF：一种通过事实核查增强学习与评估的方法，旨在提升模型输出的准确性。该方法包含两种策略：一是通过事实核查结果引导检索增强生成（RAG）过程，不更新模型参数；二是基于事实核查结果进行监督微调（SFT）或使用简单偏好优化（SimPO），以事实核查作为排序机制更新模型参数。实验针对Llama 3 70B Instruct和Llama 3 8B Instruct模型，在医疗问答任务中验证了其有效性，表明无论通过RAG增强还是自训练，都能显著提升输出的可靠性和事实正确性，为高精度信息应用提供了可行方案。
原文摘要 · Abstract (English)
Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study introduces LEAF: Learning and Evaluation Augmented by Fact-Checking, a novel approach designed to enhance the factual reliability of LLMs, with a focus on medical question answering (QA). LEAF utilizes a dual strategy to enhance the factual accuracy of responses from models such as Llama 3 70B Instruct and Llama 3 8B Instruct. The first strategy, Fact-Check-Then-RAG, improves Retrieval-Augmented Generation (RAG) by incorporating fact-checking results to guide the retrieval process without updating model parameters. The second strategy, Learning from Fact-Checks via Self-Training, involves supervised fine-tuning (SFT) on fact-checked responses or applying Simple Preference Optimization (SimPO) with fact-checking as a ranking mechanism, both updating LLM parameters from supervision. These findings suggest that integrating fact-checked responses whether through RAG enhancement or self-training enhances the reliability and factual correctness of LLM outputs, offering a promising solution for applications where information accuracy is crucial.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。