Biomedical IR

IR: Information Retrieval

Biomedical information retrieval finds evidence in resources such as PubMed, electronic health records, and biomedical knowledge graphs to support literature review, clinical question answering, trial matching, and terminology coding. Systems combine sparse search such as BM25 with dense biomedical encoders, hybrid rank fusion, query expansion, cross-encoder reranking, and structured knowledge from ontologies or constraints. Benchmarks including BioASQ, PubMedQA, TREC-COVID, and clinical-record QA tests measure relevance and downstream answer quality, but gains in retrieval do not always translate into more accurate answers. Key challenges include synthesizing evidence across documents and encounters, handling conflicting or temporally qualified claims, and maintaining performance across languages and complex relational queries.

Latest papers

43 papers7 papers in the last four weeks, up 17% on the four weeks before. 0.0% of all new papers.

How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions
Oct 22, 2026Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias +3RAG Evaluation Biomedical IR
Universidade Federal da Paraíba (UFPB), João Pessoa, PB, Brazil · Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents
Oct 21, 2026Mohammed SaqlainLLM Agent Evaluation Scientific Claim Verification
Independent Researcher, Bangalore, India
Large-Scale Biomedical RAG: Corpus Scaling, Document Representation, and Efficiency Trade-offs
Oct 19, 2026Adrián Sánchez-Freire, Gonzalo Pérez-Gómez, Aitziber Atutxa +1Retrieval-Augmented Generation RAG Evaluation
HiTZ Basque Center for Language Technology, University of the Basque Country (EHU), P.º Rafael Moreno "Pitxitxi", 2, Bilbao, 48013, Biscay, Spain
BioStudyBench: Evaluating Agents on Post-Cutoff Biomedical Studies
Oct 6, 2026David Li, Shaamil Karim, Christian GensbiglerScientific Agent Benchmarks AI Agent Benchmarks
University of Waterloo
Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study
Oct 2, 2026Yun Wang, Gad Shaulsky, Tomaž Curk +1Scientific Document Retrieval Biomedical IR
University of Ljubljana, Faculty of Computer and Information Science, Večna pot 113, 1000 Ljubljana, Slovenia · Department of Molecular and Human Genetics, Baylor College of Medicine, Baylor Plaza, Houston, TX 77030, USA
Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes
Oct 1, 2026Maryam Shahbaz Ali, Laura B. Strachan, Caitlin Sherman +3Cross-Encoder Reranking Retrieval-Augmented Generation
Children’s National Hospital, Washington, DC, USA · University of Florida, Gainesville, FL, USA · George Washington University, Washington DC, USA
Overview of BioASQ 2026: The fourteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
Sep 30, 2026Anastasios Nentidis, Georgios Katsimpras, Anastasia Krithara +18Biomedical QA Clinical Information Extraction
National Center for Scientific Research “Demokritos”, Athens, Greece · Barcelona Supercomputing Center, Barcelona, Spain · Lomonosov Moscow State University, Russia +6
A Living Benchmark for Information Retrieval from Electronic Health Records
Sep 24, 2026Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani +23Synthetic Benchmark Generation Clinical QA
Department of Biomedical Data Science, Stanford University, Stanford, CA · Department of Pathology, Stanford University, Stanford, CA · Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA +6
OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?
Sep 8, 2026Xiao Yu Cindy Zhang, Wyeth Wasserman, Jian ZhuInformation Retrieval Biomedical IR
Graduate Program in Bioinformatics, The University of British Columbia · Centre for Molecular Medicine and Therapeutics, BC Children’s Hospital Research Institute · Department of Medical Genetics, The University of British Columbia +1
BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation
Sep 4, 2026André Ribeiro, Rúben Garrido, Alexander Christiansen +2Biomedical QA Biomedical IR
IT, University of Aveiro, Aveiro, Portugal · IEETA/DETI, LASI, University of Aveiro, Aveiro, Portugal · Aalborg University Business School, Aalborg, Denmark
TWIX: a Two-Stage Approach for End-To-End Named Entity Recognition and Relation Extraction
Sep 1, 2026Marco Martinelli, Laura MenottiRelation Extraction Named Entity Recognition
Department of Information Engineering, University of Padova, Padova, Italy
Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
Aug 31, 2026Riya Ahuja, Tim Kacprowski, Roya Shiasi SardoabiRelation Extraction Document Chunking
Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany · Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany
Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
Aug 31, 2026Negin Sadat Babaiha, Stefan Geissler, Marie-Christine Simon +2Document Information Extraction Biomedical IR
Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, Sankt Augustin, Germany · Kairntech SAS, 29 Chemin du Vieux Chêne, Meylan 38240, France · Bonn-Aachen International Center for Information Technology (b-it), University of Bonn, Bonn, Germany
Case2Flow: Bridging Patient Cases and Guideline Flowcharts through Multimodal Retrieval
Aug 26, 2026Jiale Wei, Yufan Chen, Alexander Jaus +5Biomedical IR Clinical Decision Support
Karlsruhe Institute of Technology, Karlsruhe, Germany · Helmholtz Information and Data Science School for Health (HIDSS4Health), Karlsruhe/Heidelberg, Germany · University Hospital Essen, Essen, Germany
Aligning Biomedical Texts and Knowledge Graphs: A Systematic Comparison of Lightweight Alignment Strategies
Aug 24, 2026Artem Bisliouk, Elizaveta Nosova, Heiko Paulheim +2Biomedical KGs Biomedical IR
University of Mannheim, Germany · Data and Web Science Group, University of Mannheim, Germany
Large language model-assisted discovery of cohorts from scientific literature
Aug 16, 2026Moritz Sturm, Lisa M. Berg, Inken Berg +6Biomedical IR
Department of Child and Adolescent Psychiatry, Psychosomatic Medicine and Psychotherapy, University Hospital Frankfurt, Goethe University Frankfurt, Frankfurt am Main, Germany · Department of Computer Science, Goethe University Frankfurt, Frankfurt am Main, Germany · The Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany
Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions
Aug 13, 2026Qingfang Liu, Qiao Jin, Joe D. Menke +2Clinical QA Information Retrieval
National Institute on Drug Abuse Intramural Research Program, National Institutes of Health, Baltimore, MD, USA · National Library of Medicine, National Institutes of Health, Bethesda, MD, USA · School of Information Sciences, University of Illinois Urbana-Champaign, Champaign, IL, USA
Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b
Aug 2, 2026Xueying Zhao, Lee Mai, Balaji AnandganeshRetrieval-Augmented Generation Learning to Rank
Georgia Institute of Technology, North Ave NW, Atlanta, GA 30332
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
Jul 30, 2026Luigi Sigillo, Matteo Silvestri, Francesco Tabaro +9LLM Agent Orchestration Scientific QA
1EMBL Rome, European Molecular Biology Laboratory, Monterotondo, Italy. · 3Sapienza University of Rome, Italy. · 2European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK. +3
Cost-Pragmatic Quality Gating and Selection-Fusion Multi-Model Combiners for BioASQ Phases A+ and B
Jul 15, 2026Dima Galat, Marian-Andrei RizoiuRetrieval-Augmented Generation Biomedical QA
University of Technology Sydney, Australia
mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health
Jun 28, 2026Yi RenHealthcare Medical QA
École Polytechnique Fédérale de Lausanne, Switzerland
MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval
Jun 23, 2026Junhyeok Lee, Han Jang, Hyeonjin Goh +1Multilingual IR Information Retrieval
Seoul National University · Seoul National University College of Medicine · Seoul National University Hospital
Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio
Jun 15, 2026Anzhe Xie, Weihang Su, Yujia Zhou +2Systematic Review Automation AI-Assisted Scientific Research
Tsinghua University Beijing, China
Transfer Learning for FHIR Questionnaire Terminology Binding
Jun 13, 2026Maxim GorshkovTransfer Learning Biomedical IR
Department of Computer Science · Stanford University
AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction
Jun 11, 2026Fabien Maury, Solène Grosdidier, Maud de Dieuleveult +1Named Entity Recognition Document Information Extraction
Imagine - U1163, HeKA | U1346 · Inserm, Université Paris Cité, U1163 Institut Imagine, Paris, France · Imagine - U1163 +3
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
Jun 2, 2026Erfan Nourbakhsh, Rocky Slavin, Ke Yang +1Retrieval-Augmented Generation LLM Grounding
The University of Texas at San Antonio
DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering
May 31, 2026Qing Wang, Bo Li, Jialu Liang +3Biomedical QA Agentic RAG
Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Florida, USA · PAMI Research Group, Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Taipa, Macau, China
Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages
May 28, 2026David Rey-Blanco, Roberto CruzData Augmentation Healthcare
TietAI
When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering
May 13, 2026Yikun Han, Mengfei Lan, Halil KilicogluSelective Prediction Healthcare
University of Illinois Urbana-Champaign
ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
May 11, 2026Alex StinardRAG Evaluation Clinical QA
Department of Clinical Sciences, College of Medicine · University of Central Florida, Orlando, FL 32816

Oct 22, 2026J/K move · Enter open · S save

How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions

Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias, Thaís Gaudêncio+2

Universidade Federal da Paraíba (UFPB), João Pessoa, PB, Brazil · Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

RAG Evaluation Biomedical IR IR Evaluation Hybrid Retrieval

Open paper AskPDF arXiv

Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Yes/No or WH-question per document, were used. Retrieval combined dense embeddings, BM25, and cross-encoder reranking. Chunk sizes of 128 to 1024 tokens, overlaps of 0 to 20%, and four retriever configurations were evaluated. Relevance was defined by evidence spans mapped to all containing chunks, treating overlapping chunks with equivalent evidence as relevant. Retrieval was evaluated using R-Precision, Recall@K, MRR, and nDCG@K. Separately, generation was assessed on a 512-token index at K=1 to 5 using DeepEval claim-level metrics, with deepseek-v4-pro as the LLM judge, and BLEU/ROUGE metrics. Results: The selected hybrid retriever, using 384-token chunks and 20% overlap, retrieved accepted evidence in the top three results for 17 of 18 queries. Recall@3, R-Precision, MRR@3, and nDCG@3 each reached 0.94. Ground-truth curation increased evidence spans from 25 to 37 and accepted chunk targets from 36 to 51 without changing retrieval rankings. Conclusion: Cross-encoder reranking achieved the highest retrieval scores. Expanded relevance annotations increased recognized evidence without changing rankings, highlighting annotation sensitivity. The small development set and retrieval-informed curation require independent validation, including radiologist assessment of evidence sufficiency.