Weaving Multi-Source Evidence for Biomedical Reasoning: The BioMedHop Benchmark and BioWeave Framework

• URL: http://arxiv.org/abs/2606.16211v1
• Date: Mon, 15 Jun 2026 04:38:24 GMT
• Title: Weaving Multi-Source Evidence for Biomedical Reasoning: The BioMedHop Benchmark and BioWeave Framework
• Abstract summary: We introduce BioMedHop, a graph-grounded benchmark for evaluating biomedical reasoning over structured evidence topologies.<n>We propose BioWeave, a source-aware reasoning framework that retrieves biomedical KG paths, gathers supporting clues from documents and web sources, and verifies answers through entity-level evidence support.<n>BioWeave achieves the best overall performance among compared methods on BioMedHop, outperforming the strong hybrid baseline ToG-2 by 10.5% in the overall average.
• Score: 22.541216949613716
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Biomedical question answering (QA) increasingly requires reasoning over interacting entities, where supporting evidence is scattered across biomedical knowledge graphs, literature documents, and web-accessible resources. However, existing biomedical QA benchmarks mainly focus on exam-style knowledge, literature comprehension, or short-range multi-hop inference, leaving source-conditioned graph reasoning and evidence topology construction underexplored. To fill this gap, we introduce BioMedHop, a multi-source graph-grounded benchmark for evaluating biomedical reasoning over structured evidence topologies. BioMedHop contains 10,045 instances across KG, document, web, and hybrid evidence settings, covering shared-neighbor matching, intersection reasoning, path-based reasoning, and counting, with option-based, open-ended, and numeric count renderings. To support this benchmark, we further propose BioWeave, a source-aware reasoning framework that retrieves biomedical KG paths, gathers supporting clues from documents and web sources, assembles them into a unified evidence graph, and verifies answers through entity-level evidence support. Comprehensive experiments show that BioWeave achieves the best overall performance among compared methods on BioMedHop, outperforming the strong hybrid baseline ToG-2 by 10.5% in the overall average. Moreover, BioWeave consistently improves different LLM backbones and enables smaller models, such as Qwen3-4B, to achieve reasoning performance comparable to GPT-4-Turbo.

Related papers

• MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering [11.3883842897598]
  MedHopQA is a disease-centered multi-hop reasoning benchmark consisting of 1,000 expert-curated question-answer pairs.<n>Each question requires synthesis of information across two distinct Wikipedia articles, and answers are provided in an open-ended free-text format.
  arXiv  Detail & Related papers  (2026-05-12T16:32:43Z)
• PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning [10.873172077806798]
  PlantMarkerBench is a benchmark for evaluating literature-grounded plant marker evidence interpretation from full-text biological papers.<n>It spans four plant species and contains 5,550 sentence-level evidence instances annotated for marker-evidence validity, evidence type, and support strength.<n>We benchmark diverse open-weight and closed-source language models across species and prompting strategies.
  arXiv  Detail & Related papers  (2026-05-11T05:57:15Z)
• OptimusKG: Unifying biomedical knowledge in a modern multimodal graph [24.395547772712373]
  We present OptimusKG, a biomedical labeled property graph (LPG) built from structured and semi-structured resources.<n>OptimusKG contains 190,531 nodes across 10 entity types, 21,813,863 edges across 26 relation types, and 110,276,843 values across 150 distinct property keys.<n>The graph enforces a top-level schema for nodes and edges and retains granular, type-specific properties, cross-references, and provenance.
  arXiv  Detail & Related papers  (2026-04-29T23:49:34Z)
• BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature [53.894504720119805]
  We introduce BioMiner, a multi-modal extraction framework for bioactivity data extraction.<n>Within BioMiner, bioactivity semantics are inferred through direct reasoning, while chemical structures are resolved via a chemical-structure-grounded visual semantic reasoning paradigm.<n>For rigorous evaluation and method development, we establish a benchmark comprising 16,457 bioactivity entries curated from 500 publications.
  arXiv  Detail & Related papers  (2026-04-23T10:11:56Z)
• RAG-BioQA Retrieval-Augmented Generation for Long-Form Biomedical Question Answering [0.0]
  We present RAG-BioQA, a novel framework combining retrieval-augmented generation with domain-specific fine-tuning to produce evidence-based, long-form answers.<n> Experimental results on the PubMedQA dataset show significant improvements over baselines.
  arXiv  Detail & Related papers  (2025-10-02T02:49:09Z)
• HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis [55.2480439325792]
  HySemRAG is a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG)<n>System addresses limitations in existing RAG architectures through a multi-layered approach.
  arXiv  Detail & Related papers  (2025-08-01T20:30:42Z)
• Biomedical Relation Extraction via Adaptive Document-Relation Cross-Mapping and Concept Unique Identifier [35.79876359248485]
  Document-Level Biomedical Relation Extraction (Bio-RE) aims to identify relations between biomedical entities within extensive texts.<n>Previous methods often overlook the incompleteness of documents and lack the integration of external knowledge.<n>Recent advancements in large language models (LLMs) have inspired us to explore all the above issues for document-level Bio-RE.
  arXiv  Detail & Related papers  (2025-01-09T11:19:40Z)
• Causal Representation Learning from Multimodal Biomedical Observations [57.00712157758845]
  We develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets.<n>Key theoretical contribution is the structural sparsity of causal connections between modalities.<n>Results on a real-world human phenotype dataset are consistent with established biomedical research.
  arXiv  Detail & Related papers  (2024-11-10T16:40:27Z)
• BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning [77.90250740041411]
  This paper introduces BioT5+, an extension of the BioT5 framework, tailored to enhance biological research and drug discovery. BioT5+ incorporates several novel features: integration of IUPAC names for molecular understanding, inclusion of extensive bio-text and molecule data from sources like bioRxiv and PubChem, the multi-task instruction tuning for generality across tasks, and a numerical tokenization technique for improved processing of numerical data.
  arXiv  Detail & Related papers  (2024-02-27T12:43:09Z)
• Diversifying Knowledge Enhancement of Biomedical Language Models using Adapter Modules and Knowledge Graphs [54.223394825528665]
  We develop an approach that uses lightweight adapter modules to inject structured biomedical knowledge into pre-trained language models. We use two large KGs, the biomedical knowledge system UMLS and the novel biochemical OntoChem, with two prominent biomedical PLMs, PubMedBERT and BioLinkBERT. We show that our methodology leads to performance improvements in several instances while keeping requirements in computing power low.
  arXiv  Detail & Related papers  (2023-12-21T14:26:57Z)
• EBOCA: Evidences for BiOmedical Concepts Association Ontology [55.41644538483948]
  This paper proposes EBOCA, an ontology that describes (i) biomedical domain concepts and associations between them, and (ii) evidences supporting these associations. Test data coming from a subset of DISNET and automatic association extractions from texts has been transformed to create a Knowledge Graph that can be used in real scenarios.
  arXiv  Detail & Related papers  (2022-08-01T18:47:03Z)

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.