LEAF：通过事实核查增强的学习与评估方法以提升大语言模型的事实性
LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models
AI总结：
针对大语言模型事实准确性不足的问题，提出LEAF框架，通过“先核查再RAG”和基于事实核查的自训练双重策略，有效提升医疗问答场景下模型输出的事实可靠性。
摘要：
大语言模型（LLM）在各类自然语言处理任务中展现出卓越能力，但在维持事实准确性方面常存在不足，在医疗等知识密集型领域尤为突出。本研究提出LEAF（通过事实核查增强的学习与评估方法），这是一种旨在提升LLM事实可靠性的新方法，聚焦于医疗问答（QA）场景。LEAF采用双重策略提升Llama 3 70B Instruct和Llama 3 8B Instruct等模型回复的事实准确性。第一种策略为“先核查再检索增强生成（Fact-Check-Then-RAG）”，通过引入事实核查结果指导检索过程来改进检索增强生成（RAG），无需更新模型参数。第二种策略为“通过自训练从事实核查中学习”，包括对经事实核查的回复进行有监督微调（SFT），或应用以事实核查作为排序机制的简单偏好优化（SimPO），二者均通过监督信号更新LLM参数。研究结果表明，无论是通过RAG增强还是自训练方式，整合经事实核查的回复都能提升LLM输出的可靠性与事实正确性，为信息准确性至关重要的应用场景提供了有前景的解决方案。
英文摘要：
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.
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。
