RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
This work addresses the challenge of improving logical coherence and factual integrity in LLMs for domains like commonsense and medical reasoning, representing an incremental advancement in retrieval-augmented reasoning methods.
The paper tackles the problem of enhancing reasoning accuracy and factual integrity in large language models for complex knowledge-intensive tasks by introducing RARE, a retrieval-augmented extension to the mutual reasoning framework. Experimental results with LLaMA 3.1 show that RARE enables open-source LLMs to achieve competitive performance with top models like GPT-4 and GPT-4o.
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.