跳到正文
arXiv:cs.CL· Ziyang Ling, Ziyi Chen, Ronald X. Xu, Mingzhai Sun·· 7 小时前

ReSemReason:面向生物医学多跳问答的关系语义推理框架

Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA

AI 导读

ReSemReason 关系语义推理框架通过让候选发现与证据选择共享问题诱导的关系模式分布,解决生物医学多跳问答中答案可达但证据无效的问题。其 ReSemAttn 采用关系条件化的 key/value 投影与不确定性加权路径先验来关注候选证据,并以绝对支持分数补充归一化注意力。在 BioHopR、PrimeKGQA 和 MedReason 上的实验显示答案排序与答案集质量均有提升。

正文

View PDF HTML (experimental)

Abstract:Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing methods can retrieve correct answers, yet often rank them poorly within a large pool of seemingly relevant candidates. Even when a correct answer is retrieved, its associated evidence and reasoning path may fail to support the relation composition required by the question. We term this disconnect between answer reachability and evidential validity the reachable-but-invalid problem. We present ReSemReason, which shares a question-induced distribution over typed, directed relation schemas between candidate discovery and evidence selection. Schema compatibility guides graph search; ReSemAttn then uses relation-conditioned key/value projections and an uncertainty-weighted path prior to attend to candidate-specific evidence. A separate absolute-support score complements normalized attention when all retrieved paths are weak. The reported experiments on BioHopR, PrimeKGQA, and MedReason show improvements in answer ranking and answer-set quality. Path-discrimination analyses examine the distinction between endpoint correctness and evidential support. We also specify matched controls for search, attention, and schema uncertainty.
Subjects: Computation and Language (cs.CL)
Cite as: arXiv:2610.19754 [cs.CL]
  (or arXiv:2610.19754v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2610.19754

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ziyi Chen [view email]
[v1] Wed, 14 Oct 2026 08:09:02 UTC (7,137 KB)

来源:arXiv:cs.CL · arxiv.org