RCER：为迭代式RAG重建跨证据关系
原标题：RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation
AI 摘要
研究者提出 RCER，一种迭代式检索增强生成（RAG）方法，通过从累积的源段落中重建跨证据关系来改进多跳问答。该方法包含轮间关系证据获取、推理上下文重建和跨证据组合推理三个环节，用于动态分解问题并指导检索。在三个多跳 QA 基准上，RCER 平均比最佳基线提升 2.83 EM 和 3.06 F1，并在叙事与隐式推理任务上表现更优。
正文节选
RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation Abstract Iterative retrieval-augmented generation (RAG) accumulates knowledge from retrieved evidence to answer complex questions, but existing methods struggle to reconstruct entity correspondences and inferential dependencies across retrieved passages as new information emerges. We propose RCER, an iterative RAG method that reconstructs these cross-evidence relations directly from accumulated source pass