Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation
This addresses the issue of degraded performance in RAG systems for users relying on LLMs for accurate information retrieval and generation, though it appears incremental as it builds on existing RAG frameworks.
The paper tackles the problem of erroneous or distracting information in retrieved documents for Retrieval-Augmented Generation (RAG) by introducing a plug-in module that refines chunks to enhance accuracy and contextual appropriateness in LLM outputs.
Retrieval-Augmented Generation (RAG) aims to augment the capabilities of Large Language Models (LLMs) by retrieving and incorporate external documents or chunks prior to generation. However, even improved retriever relevance can brings erroneous or contextually distracting information, undermining the effectiveness of RAG in downstream tasks. We introduce a compact, efficient, and pluggable module designed to refine retrieved chunks before using them for generation. The module aims to extract and reorganize the most relevant and supportive information into a concise, query-specific format. Through a three-stage training paradigm - comprising supervised fine - tuning, contrastive multi-task learning, and reinforcement learning-based alignment - it prioritizes critical knowledge and aligns it with the generator's preferences. This approach enables LLMs to produce outputs that are more accurate, reliable, and contextually appropriate.