重新思考检索增强作为合成:一种查询感知的上下文合并方法
Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
AI总结:
本文提出MergeRAG框架,通过查询感知合成优化检索增强过程,提升信息密度和效率,实验表明在F1和精确匹配上优于现有方法。
摘要:
检索增强生成(RAG)使大语言模型(LLMs)能够通过动态整合外部信息扩展其现有知识。然而,实际部署受限于LLM的有限上下文窗口,迫使在信息充分性和token消耗之间做出权衡。标准流程通过检索后选择策略解决,通常仅保留相关性最高的前k个片段。然而,这种方法效率低下:它本质上截断了相关性分布长尾中的关键桥梁证据,同时浪费token预算在语义冗余的高排名片段上。本文重新思考检索增强作为动态优化问题,旨在最大化信息密度。我们提出MergeRAG,一种新颖的框架,将范式从静态过滤转向查询感知合成。MergeRAG采用评分代理通过双路径机制重构检索上下文:1)对称合并,将弱信号整合以恢复丢失的桥梁证据;2)不对称合并,利用熵引导锚定以消除冗余而不牺牲语义完整性。我们进一步引入分层并行合并策略,以减少信息损失并最大化计算并行性。在标准基准上的广泛实验表明,MergeRAG显著优于现有RAG基线,分别在F1得分和精确匹配(EM)上提高13.7和11.5点。
英文摘要:
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information. However, practical deployment is fundamentally constrained by the LLM's finite context window, forcing a trade-off between information sufficiency and token consumption. Standard pipelines address this via a retrieve-then-select strategy, typically retaining only the top-k chunks based on relevance. Nevertheless, this approach is suboptimal: it inherently truncates critical bridging evidence located in the long tail of the relevance distribution, while simultaneously wasting the token budget on semantically redundant high-ranking chunks. In this paper, we rethink retrieval-augmentation as a dynamic optimization problem aimed at maximizing information density. We propose MergeRAG, a novel framework that shifts the paradigm from static filtering to query-aware synthesis. MergeRAG employs a scoring agent to restructure retrieved contexts through a dual-pathway mechanism: 1) Symmetric Merging, which consolidates weak signals to recover lost bridging evidence; 2) Asymmetric Merging, which utilizes entropy-guided anchoring to eliminate redundancy without sacrificing semantic integrity. We further introduce a Hierarchical Parallel Merging strategy that mitigates information loss while maximizing computational parallelism. Extensive experiments on standard benchmarks demonstrate that MergeRAG significantly outperforms state-of-the-art RAG baselines, achieving up to 13.7 points improvement in F1 score and 11.5 points in Exact Match (EM), respectively.
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。