RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models

作者：Hieu Tran, Zonghai Yao, Zhichao Yang, Junda Wang, Yifan Zhang, Shuo Han, Feiyun Ouyang, Yu Hong · 年份：2025 · DOI：10.18653/v1/2025.acl-long.896 · 被引用次数：6 · 研究领域：Topic Modeling、Natural Language Processing Techniques

, 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 closed-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.