MEGRAG：面向答案感知多跳检索增强生成的多粒度证据图
MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG
浏览论文内容
中文总结 AI 辅助
本文提出MEGRAG框架，将多跳推理转化为路径结构的多粒度证据图，通过跨粒度索引关联多粒度证据，按需选择证据并迭代判断查询是否解决，在多跳问答任务上较各类RAG基准取得持续性能提升。
中文摘要 AI 辅助
多跳问答是检索增强生成（RAG）领域的核心挑战，因为推导答案需要整合分散的证据。迭代RAG（iRAG）被广泛用于应对这一挑战，但现有方法存在两个局限：其一，多数方法仍以单粒度证据支撑每一步推理，难以平衡信息密度与上下文噪声；其二，现有方法往往仅在聚合中间步骤检索到的证据后才回答原始问题，冗余证据与中间检索错误可能累积，进而降低最终答案质量。为解决这些局限，本文提出MEGRAG，这是一个答案感知框架，将多跳推理表示为路径结构的多粒度证据图。离线阶段，MEGRAG通过跨粒度索引将段落与其句子、提取的三元组关联；在线阶段，它为当前查询检索段落并选择对齐证据，从紧凑三元组开始，按需添加句子或段落上下文。MEGRAG利用所得中间答案与先前推理结果判断初始查询是否已解决：若未解决，识别缺失信息并制定聚焦的下一个查询；若已解决，则停止检索并返回答案。大量实验表明，MEGRAG在各类RAG基准上均取得了持续提升。
英文摘要
Multi-hop question answering is a fundamental challenge in retrieval-augmented generation (RAG), because deriving an answer requires integrating dispersed evidence. Iterative RAG (iRAG) is widely used for this challenge, but existing methods have two limitations. First, most methods still support each reasoning step with single-granularity evidence, making it difficult to balance information density and contextual noise. Second, existing methods often answer the original question only after aggregating evidence retrieved across intermediate steps, so redundant evidence and intermediate retrieval errors may accumulate and degrade the final answer. To address these limitations, we propose MEGRAG, an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph. Offline, MEGRAG links passages to their sentences and extracted triples through a cross-granularity index. Online, it retrieves passages for the current query and selects aligned evidence, starting with compact triples and adding sentence or passage context as needed. MEGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved. If not, it identifies the missing information and formulates a focused next query; otherwise, it stops retrieval and returns the answer. Extensive experiments demonstrate consistent gains over a diverse set of RAG baselines.
