arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.13019cs.CL
收藏

Oreo:一个用于增强检索增强生成的即插即用上下文重构器

Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation

Virginia Tech(弗吉尼亚理工大学)

Sha Li, Naren Ramakrishnan

AI总结:

本文提出Oreo,一个紧凑高效的可插拔模块,通过三阶段训练范式优化检索增强生成中的检索文本块,提取重组关键信息以对齐生成器偏好,从而提升LLM输出的准确性和可靠性。

摘要:

检索增强生成(RAG)旨在通过在生成前检索并融入外部文档或文本块来增强大型语言模型(LLMs)的能力。然而,即使检索器的相关性有所提升,仍可能引入错误或在上下文上分散注意力的信息,从而削弱RAG在下游任务中的有效性。我们引入了一个紧凑、高效且可插拔的模块,旨在使用检索到的文本块进行生成之前对其进行优化。该模块旨在提取并重组最相关和最具支持性的信息,形成简洁的、特定于查询的格式。通过三阶段训练范式——包括监督微调、对比多任务学习和基于强化学习的对齐——它优先处理关键知识并使其与生成器的偏好对齐。这种方法使LLMs能够生成更准确、可靠且上下文适宜的输出。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑