针对生物医学问答的复杂路径搜索难题，提出自适应路径查找框架AdaPath。
AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA
- 从路径库中检索与查询自适应的元路径，融合语义与图结构信息。
- 在多跳问答中保持稳定性能，即使查询不暴露中间推理过程。
- 适合生物医学知识图谱问答研究者，尤其关注路径推理机制者。
在知识图谱上进行路径查找已成为将大模型推理锚定于多跳问题的有效方法。然而，生物医学问答引入了两个通用方法未设计应对的挑战：(i) 查询不暴露中间推理过程，可通过多种有效路径解答；(ii) 生物医学知识图谱连接密集，路径查找方法易误入歧途。为此，我们提出AdaPath，一种从路径库（Path-Bank）中检索查询自适应元路径的路径查找框架，该框架同时捕捉查询语义与生物医学知识图结构。AdaPath在生物医学查询中提供缺失线索，同时在多跳推理过程中有效剪枝密集邻居。我们进一步发布BioStrat-QA，一个按中间推理暴露程度分层的生物医学知识图谱问答基准。在多个生物医学知识图谱问答基准上，AdaPath持续优于基线，在多跳查询暴露较少表面信息时仍能维持有意义的路径查找。源代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。