用检索增强推理，让大模型在医学等复杂任务中更准确、更可信。
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
- 在MCTS框架中加入检索生成与重答子问题机制，提升推理质量。
- 在LLaMA 3.1上达到GPT-4水平的推理准确性与事实一致性。
- 适合需要高可信度推理的医疗、常识等专业领域应用。
本文提出RARE（检索增强推理增强），作为rStar互斥推理框架的通用扩展，旨在提升大语言模型在常识推理和医疗等知识密集型复杂任务中的推理准确性和事实完整性。RARE在蒙特卡洛树搜索（MCTS）框架内引入两项创新动作：A6基于初始问题生成搜索查询，通过检索获取相关信息并融合到推理中以生成最终答案；A7则针对生成的子问题进行信息检索，并用上下文信息重新回答这些子问题。此外，提出一种检索增强的事实性评分器替代原判别器，优先选择符合高事实标准的推理路径。实验结果表明，使用LLaMA 3.1时，RARE使开源模型性能达到GPT-4与GPT-4o相当水平。该研究确立了RARE在逻辑连贯性与事实完整性至关重要的领域中提升大模型能力的可扩展性方案。
原文摘要 · Abstract (English)
This work introduces RARE (Retrieval-Augmented Reasoning Enhancement), a versatile extension to the mutual reasoning framework (rStar), aimed at enhancing reasoning accuracy and factual integrity across large language models (LLMs) for complex, knowledge-intensive tasks such as commonsense and medical reasoning. RARE incorporates two innovative actions within the Monte Carlo Tree Search (MCTS) framework: A6, which generates search queries based on the initial problem statement, performs information retrieval using those queries, and augments reasoning with the retrieved data to formulate the final answer; and A7, which leverages information retrieval specifically for generated sub-questions and re-answers these sub-questions with the relevant contextual information. Additionally, a Retrieval-Augmented Factuality Scorer is proposed to replace the original discriminator, prioritizing reasoning paths that meet high standards of factuality. Experimental results with LLaMA 3.1 show that RARE enables open-source LLMs to achieve competitive performance with top open-source models like GPT-4 and GPT-4o. This research establishes RARE as a scalable solution for improving LLMs in domains where logical coherence and factual integrity are critical.
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。