AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA

• URL: http://arxiv.org/abs/2608.30556v1
• Date: Mon, 31 Aug 2026 10:32:23 GMT
• Title: AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA
• Abstract summary: We propose AdaPath, a path-finding framework that retrieves query-adaptive meta-paths from Path-Bank.<n>AdaPath provides the missing cues in biomedical queries while effectively pruning dense knowledge graph neighborhoods.<n>We release BioStrat-QA, a benchmark that stratifies multi-hop queries by how much intermediate reasoning they expose.
• Score: 54.439095132552325
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering [10.112212302226615]
  We present S-Path-RAG, a framework to improve multi-hop question answering over large knowledge graphs.<n>S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths.<n>We validate S-Path-RAG on standard multi-hop KGQA benchmarks and through ablations and diagnostic analyses.
  arXiv  Detail & Related papers  (2026-03-05T14:22:23Z)
• UETQuintet at BioCreative IX - MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval [0.0]
  We propose a model designed to effectively address both direct and sequential questions.<n>We leverage multi-source information retrieval and in-context learning to provide rich, relevant context for generating answers.<n>Our approach achieves an Exact Match score of 0.84, ranking second on the current leaderboard.
  arXiv  Detail & Related papers  (2026-01-11T16:12:38Z)
• Soft Reasoning Paths for Knowledge Graph Completion [41.04734533217766]
  Reasoning paths are reliable information in knowledge graph completion (KGC)<n>In real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities.<n>We introduce soft reasoning paths to make the proposed algorithm more stable against missing path circumstances.
  arXiv  Detail & Related papers  (2025-05-06T08:12:48Z)
• ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation [37.72627790771535]
  We propose a novel subgraph inference framework, ExPAth, that explicitly integrates experimental data to classify various graphs (bio-networks) in biological databases.<n>Our framework can seamlessly integrate biological foundation models to encode the experimental molecular data.<n>Experiments involving 301 bio-networks evaluations demonstrate that pathways inferred by ExPath are biologically meaningful.
  arXiv  Detail & Related papers  (2025-02-25T09:33:15Z)
• BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning [49.487327661584686]
  We introduce BioMaze, a dataset with 5.1K complex pathway problems from real research.<n>Our evaluation of methods such as CoT and graph-augmented reasoning, shows that LLMs struggle with pathway reasoning.<n>To address this, we propose PathSeeker, an LLM agent that enhances reasoning through interactive subgraph-based navigation.
  arXiv  Detail & Related papers  (2025-02-23T17:38:10Z)
• K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction [21.72997408572975]
  K-Paths is a model-agnostic retrieval framework that extracts structured, diverse, and biologically meaningful multi-hop paths from dense biomedical knowledge graphs.<n>These paths enable the prediction of unobserved drug-drug and drug-disease interactions.<n>Experiments show that K-Paths improves zero-shot reasoning across state-of-the-art language models.
  arXiv  Detail & Related papers  (2025-02-18T23:55:24Z)
• DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research [96.10765714077208]
  Traditional keyword-based search engines fall short in assisting users who may not be familiar with specific terminologies. We present a knowledge graph-based paper search engine for biomedical research to enhance the user experience. The system, dubbed DiscoverPath, employs Named Entity Recognition (NER) and part-of-speech (POS) tagging to extract terminologies and relationships from article abstracts to create a KG.
  arXiv  Detail & Related papers  (2023-09-04T20:52:33Z)
• Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results [60.4817465598352]
  We introduce an original variant of Monte-Carlo Tree Search (MCTS) tailored to multi-agent pathfinding. Specifically, we use individual paths to assist the agents with the the goal-reaching behavior. We also use a dedicated decomposition technique to reduce the branching factor of the tree search procedure.
  arXiv  Detail & Related papers  (2023-07-25T12:33:53Z)
• UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph [89.98762327725112]
  Multi-hop Question Answering over Knowledge Graph(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question. We propose UniKGQA, a novel approach for multi-hop KGQA task, by unifying retrieval and reasoning in both model architecture and parameter learning.
  arXiv  Detail & Related papers  (2022-12-02T04:08:09Z)
• Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs [31.088325888508137]
  This paper proposes improving multi-hop KGQA by exploiting relation paths' hybrid semantics. We integrate explicit textual information and implicit KG structural features of relation paths based on a novel rotate-and-scale entity link prediction framework.
  arXiv  Detail & Related papers  (2022-09-02T08:07:37Z)
• Modeling Multi-hop Question Answering as Single Sequence Prediction [88.72621430714985]
  We propose a simple generative approach (PathFid) that extends the task beyond just answer generation. PathFid explicitly models the reasoning process to resolve the answer for multi-hop questions. Our experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets.
  arXiv  Detail & Related papers  (2022-05-18T21:57:59Z)
• A Complex KBQA System using Multiple Reasoning Paths [42.007327947635595]
  Multi-hop knowledge based question answering (KBQA) is a complex task for natural language understanding. We introduce an end-to-end KBQA system which can leverage multiple reasoning paths' information and only requires labeled answer as supervision.
  arXiv  Detail & Related papers  (2020-05-22T02:35:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.