RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts

TL;DR

This paper presents RAG-RLRC-LaySum, a novel framework combining retrieval-augmented generation and reinforcement learning to produce accurate, relevant, and highly readable lay summaries of biomedical texts, improving public understanding of complex research.

Contribution

The paper introduces a new framework integrating retrieval-augmented generation with readability control for biomedical summarization, surpassing existing models in multiple evaluation metrics.

Findings

20% increase in readability scores

15% improvement in ROUGE-2 relevance scores

10% enhancement in factual accuracy

Abstract

This paper introduces the RAG-RLRC-LaySum framework, designed to make complex biomedical research understandable to laymen through advanced Natural Language Processing (NLP) techniques. Our Retrieval Augmented Generation (RAG) solution, enhanced by a reranking method, utilizes multiple knowledge sources to ensure the precision and pertinence of lay summaries. Additionally, our Reinforcement Learning for Readability Control (RLRC) strategy improves readability, making scientific content comprehensible to non-specialists. Evaluations using the publicly accessible PLOS and eLife datasets show that our methods surpass Plain Gemini model, demonstrating a 20% increase in readability scores, a 15% improvement in ROUGE-2 relevance scores, and a 10% enhancement in factual accuracy. The RAG-RLRC-LaySum framework effectively democratizes scientific knowledge, enhancing public engagement with biomedical discoveries.