AdaPath：基于路径库的查询自适应路径查找用于多跳隐式生物医学知识图谱问答
AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA
- KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对生物医学KGQA的两个挑战，提出AdaPath框架，通过Path-Bank检索查询自适应元路径，发布BioStrat-QA基准，在多个生物医学KGQA基准上性能优于基线。
AI中文摘要：
知识图谱上的路径查找已成为将大语言模型（LLM）推理落地到多跳问题的有效方式。然而，生物医学问答存在通用领域方法未设计应对的两个独特挑战：一是查询未暴露中间推理过程，且可通过多条有效路径解答；二是生物医学知识图谱连接密集，路径查找方法易出现错误转向。为应对这些挑战，本文提出AdaPath，这是一种路径查找框架，可从路径库（Path-Bank）中检索查询自适应元路径，该路径库同时捕获查询语义与生物医学知识图谱结构。AdaPath在多跳推理期间为生物医学查询提供缺失线索，同时有效修剪密集知识图谱邻域。本文还发布BioStrat-QA，这是一个生物医学知识图谱问答基准，按多跳查询暴露中间推理的程度对其进行分层。在多个生物医学知识图谱问答基准上，AdaPath始终优于基线，即使多跳查询暴露的表面信息较少，也能维持有意义的路径查找。源代码可在指定URL获取。
英文摘要：
Path-finding over knowledge graphs has become an effective way to ground LLM reasoning on multi-hop questions. However, biomedical QA introduces two distinct challenges that general-domain methods are not designed for: (i) queries do not expose intermediate reasoning and can be answered through multiple valid pathways, and (ii) biomedical knowledge graphs are densely connected, so path-finding methods easily take wrong turns. To address these challenges, we propose AdaPath, a path-finding framework that retrieves query-adaptive meta-paths from Path-Bank, which captures both query semantics and biomedical knowledge graph structure. AdaPath provides the missing cues in biomedical queries while effectively pruning dense knowledge graph neighborhoods during multi-hop reasoning. We further release BioStrat-QA, a biomedical KGQA benchmark that stratifies multi-hop queries by how much intermediate reasoning they expose. Across biomedical KGQA benchmarks, AdaPath consistently outperforms baselines, sustaining meaningful path-finding even when multi-hop queries expose less surface information. The source code is available at https://github.com/Jun-Hyeong-Kim/AdaPath.
