SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation

TL;DR

SeRTS introduces a novel self-rewarding tree search method that enhances biomedical document retrieval in LLM-based RAG systems, significantly improving accuracy and efficiency for medical knowledge queries.

Contribution

The paper presents SeRTS, a plug-and-play LLM retrieval method combining Monte Carlo Tree Search and self-rewarding paradigms, improving zero-shot retrieval and fine-tuning with PPO for biomedical QA.

Findings

SeRTS outperforms baseline retrieval methods on BioASQ-QA dataset.

SeRTS improves LLMs' ability to retrieve relevant biomedical documents.

SeRTS generates higher-quality feedback for PPO training.

Abstract

Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG). However, existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries, resulting in sub-optimal performance. To address these limitations, we propose a novel plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm. By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG. We further enhance retrieval performance by fine-tuning LLMs with Proximal Policy Optimization (PPO) objectives using the trajectories collected by SeRTS as feedback. Controlled experiments using the BioASQ-QA dataset with GPT-3.5-Turbo and LLama2-7b demonstrate that our method significantly improves the performance of the BM25 retriever and surpasses the strong baseline of self-reflection in both efficiency and scalability. Moreover, SeRTS generates higher-quality feedback for PPO training than self-reflection. Our proposed method effectively adapts LLMs to document retrieval tasks, enhancing their ability to retrieve highly relevant documents for RAG in the context of medical knowledge queries. This work presents a significant step forward in leveraging LLMs for accurate and comprehensive biomedical question answering.