EviReform：面向多跳图检索的证据引导式查询重构

中文摘要 AI 辅助

多跳检索必须共同恢复提供充分证据的段落。初始段落常能解决问题中隐含的实体或关系，仅在检索开始后才更容易描述缺失的证据。图检索通过存储的语料库结构提升对相关证据的访问，但它的检索信号通常源自原始问题；即使已观测到的段落提供了更直接的语义线索，仍需通过存储的关系获取补充证据。我们提出EviReform，它将检索请求的修订与图中证据的聚合分离开来，已检索的源段落会为未解决的信息需求生成残差查询；原始和残差检索信号被分别归一化、组合，并在共享实体的命题间传播。在2WikiMultiHopQA、HotpotQA和MuSiQue数据集上，EviReform的表现超出最强基线模型，在Recall@5指标上最高提升5.59个百分点，在F1指标上最高提升4.50个百分点。这些结果表明，已观测到的证据可引导图检索，指向原始问题未充分明确的支持链部分。代码可在该网址获取：https://

英文摘要

Multi-hop retrieval must recover passages that provide sufficient evidence together. An initial passage often resolves an entity or relation implicit in the question, making the missing evidence easier to describe only after retrieval begins. Graph retrieval improves access to related evidence through stored corpus structure, but its retrieval signal is commonly derived from the original question. Complementary evidence must then be reached through stored relations even when an observed passage provides a more direct semantic cue. We introduce EviReform, which separates revising the retrieval request from aggregating evidence in the graph. Retrieved source passages formulate residual queries for the unresolved information need. The original and residual retrieval signals are normalized separately, combined, and propagated between propositions that share entities. On 2WikiMultiHopQA, HotpotQA, and MuSiQue, EviReform exceeds the strongest baseline by up to 5.59 Recall@5 points and 4.50 F1 points. These results show that observed evidence can guide graph retrieval toward the part of a supporting chain left underspecified by the original question. Code is available at https://github.com/XrazyMee/EviReform.

发表机构

• Nanjing University of Information Science and Technology（南京信息工程大学）
• Meituan（美团）

机构由 AI 辅助整理，请以论文原文为准。