用集合选择取代排序，提升复杂问答的检索效果
Shifting from Ranking to Set Selection for Retrieval Augmented Generation
- 通过思维链分析查询信息需求，全局选最优文本集合
- 在多跳问答任务中准确率超越主流开源与闭源模型
- 适合需要精准综合信息的复杂查询场景
检索增强生成（RAG）中的检索环节需确保所选段落不仅单个相关，且整体构成完整信息集。现有方法主要基于个体相关性对前k个段落进行重排序，难以满足复杂多跳问题的信息需求。本文提出一种面向集合的段落选择方法SETR，通过思维链推理显式识别查询的信息需求，并选取能共同满足这些需求的最优段落集合。在多跳RAG基准测试中，SETR在答案正确性和检索质量上均优于主流闭源大模型重排序器及开源基线，为RAG系统提供了一种高效可靠的替代方案。代码已开源：https://github.com/LGAI-Research/SetR
原文摘要 · Abstract (English)
Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing approaches primarily rerank top-k passages based on their individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering. In this work, we propose a set-wise passage selection approach and introduce SETR, which explicitly identifies the information requirements of a query through Chain-of-Thought reasoning and selects an optimal set of passages that collectively satisfy those requirements. Experiments on multi-hop RAG benchmarks show that SETR outperforms both proprietary LLM-based rerankers and open-source baselines in terms of answer correctness and retrieval quality, providing an effective and efficient alternative to traditional rerankers in RAG systems. The code is available at https://github.com/LGAI-Research/SetR
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。