提升大模型生成质量，通过重构检索内容消除干扰信息
Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation
- 引入可插拔模块，重排检索到的信息以聚焦关键内容
- 三阶段训练使生成结果更准确且贴合查询意图
- 适合需要高可靠性文本生成的场景，如医疗或法律
检索增强生成（RAG）通过在生成前检索外部文档来增强大语言模型的能力。然而，即使检索相关性提高，仍可能引入错误或干扰信息，影响下游任务效果。本文提出一个轻量、高效且可插拔的上下文重构模块，在生成前对检索到的内容进行精炼。该模块将最相关、支持性的信息提取并重组为简洁、针对查询的格式。通过监督微调、对比多任务学习和基于强化学习的对齐三个阶段训练，优先处理关键知识并使其与生成器偏好对齐。该方法使大语言模型输出更准确、可靠且语境恰当。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。