Clinical QA

QA: Question Answering

Clinical question answering studies how AI systems answer medical questions, from exam-style queries to patient-specific questions over electronic health records, guidelines, and research. Common approaches include fine-tuning and prompting language models, retrieval-augmented generation, structured queries and knowledge graphs, and agent workflows that search, verify, or cite evidence. Evaluation spans medical QA benchmarks, clinician-reviewed open-ended questions, and tasks involving longitudinal records, with growing attention to grounding, privacy, consistency, and safe abstention. A central challenge is that fluent or correct-looking answers may omit important evidence or contain unsupported claims, especially when questions require multi-step reasoning across sources or encounters.

Latest papers

63 papers12 papers in the last four weeks, up 140% on the four weeks before. 0.1% of all new papers.

EXCISE: Locating and Excising Distracting Sentences in Medical Question Answering
Oct 26, 2026Yerim Hong, Sohyun Son, Heeseung Chung +1Language Model Robustness Clinical QA
Kyung Hee University
DocTalk: Enhancing Medical Knowledge Retrieval via Fine-tuned Large Language Models with Chain-of-Thought Reasoning for Robust Clinical Decision Support
Oct 26, 2026Asad Gohar, Md Ariful Islam Mozumder, Moon-Il Joo +1Clinical QA EHR QA
Institute of Digital Anti-Aging HealthCare, Inje University, Gimhae 50834, Republic of Korea
AusClinBench: a deterministically scored benchmark of large language models against current Australian clinical policy
Oct 22, 2026Daniel S. EpsteinClinical Language Model Evaluation Clinical QA
Department of General Practice, Monash University, Melbourne, Victoria, Australia · The Long Game Project, Melbourne, Victoria, Australia
IndoNutriQA: An Indonesian Clinical Nutrition Question Answering Benchmark
Oct 22, 2026Tirana Noor Fatyanosa, Ummu Ditya Erliana, Mahendra Data +3Clinical QA Healthcare
Universitas Brawijaya · Universitas Ma Chung · MBZUAI
Trust the Edge, Doubt the Arrow: Auditing Validation Signals for Text-Mined Clinical Causal Knowledge Graphs
Oct 17, 2026Su Lan, Shicheng Zhou, Yiqi Wang +3Biomedical KGs Clinical Information Extraction
School of Information and Communication Technology, Griffith University, Gold Coast, QLD, Australia
BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment
Oct 6, 2026Kemal Davaslioglu, Nathan Conger, Sastry Kompella +2Graph Retrieval-Augmented Generation Clinical Decision Support
Nexcepta, Gaithersburg, MD, USA · United States Military Academy, West Point, NY, USA
Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering
Oct 5, 2026Aditya Tanna, Abhishek JindalReward Modeling RL for Language Model Reasoning
Dhirubhai Ambani University Gandhinagar, Gujarat, India
Auditable Clinical Timeline Reconstruction with Provenance-Aware Evidence Graphs
Oct 5, 2026Judith Jeyafreeda AndrewData Provenance Clinical QA
Public Health Unit, Medical Information Department, Bordeaux University Hospital (CHU Bordeaux), Bordeaux, France.
MS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge
Oct 5, 2026Abdul Basit, Muhammad Abdullah Hanif, Muhammad ShafiqueLLM Evaluation Synthetic Benchmark Generation
eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, UAE
Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models
Oct 1, 2026Manan Roy Choudhury, Suparno Roy Chowdhury, Swastik Sahoo +5Clinical QA Table QA
Arizona State University, Tempe, Arizona, USA · Mayo Clinic, Phoenix, Arizona, 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
GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events
Oct 1, 2026Chaiho Shin, Kwangsoo KimEvidence-Grounded Reasoning Clinical Outcome Prediction
Interdisciplinary Program of Medical Informatics, Seoul National University College of Medicine · Department of Transdisciplinary Medicine, Seoul National University Hospital · Center for Data Science, Healthcare AI Research Institute, Seoul National University Hospital +1
EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning
Sep 30, 2026Yitong Qiao, Yancheng Jin, Lei Liu +4Evidence-Grounded Reasoning AI Agent Benchmarks
Zhejiang University · Ant Healthcare, Ant Group
ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering
Sep 28, 2026Yuyan ChenClinical QA Agentic RAG
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
Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering
Sep 14, 2026Jiashuo Zhang, Yuling Chen, Yvonne Commodore-Mensah +1LLM Grounding LLM Answer Verification
Department of Computer Science Johns Hopkins University · School of Nursing Johns Hopkins University
ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information
Sep 12, 2026Antonino Vaccarella, Riccardo Cantini, Domenico Talia +4Clinical QA LLM Agents
Department of Computer Science, University of Pisa, Pisa, Italy · Department of Computer Engineering, Modeling, Electronics and Systems, University of Calabria, Rende, Italy. · Institute of Information Science and Technologies “Alessandro Faedo”, National Research Council, Pisa, Italy. +2
SentryLine: Evidence-Grounded Question Answering over Evolving Documents in Oncology Care
Sep 8, 2026Tampu Ravi Kumar, Gaurav Najpande, Muhammad Ali Khan +7Question Answering Clinical QA
Arizona State University · Mayo Clinic · Jawaharlal Nehru Medical College
ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues
Sep 1, 2026Huimin Wang, Zhengyi Zhao, Yutian ZhaoClinical QA Clinical Reasoning
Shenzhen University · The Chinese University of Hong Kong · Dealism
Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines
Aug 28, 2026Jie Hu, Junjie Wang, Shan Lu +3Clinical QA Evidence Selection
Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing, 211166, China · Department of Maternal and Child Care, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China · Department of Geriatrics, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China +2
Performance of a domain-specific large language model in answering patient questions in psychiatry
Aug 24, 2026Alexander J. Hish, Arjun Nagendran, Scott N. ComptonMedical LLMs Medical QA
Pritzker Department of Psychiatry and Behavioral Health, Lurie Children's Hospital of Chicago, Chicago, IL, USA · Relativ.ai, USA · Northwestern University Feinberg School of Medicine, Chicago, IL, USA
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
Grounded in Consensus, In Step With Emerging Science: A Consensus-Anchored Multi-Corpus Clinical Chatbot for Long COVID
Jul 27, 2026Yining Wu, Philip DiGiacomo, Ying Ding +1Retrieval-Augmented Generation Clinical Decision Support
School of Information University of Texas at Austin Austin, TX, USA · Department of Computer Science University of Texas at Austin Austin, TX, USA · School of Information, Dell Medical School University of Texas at Austin Austin, TX, USA +1
CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series
Jul 10, 2026Frank Nie, Ethan B. Liu, Yuan Zhu +3Irregular Time-Series Modeling Time Series QA
Shandong University China · University of Auckland New Zealand
Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention
Jul 1, 2026William Philipp, Finn Fassbender, Daniel Fister +12Multilingual Language Model Evaluation LLM-as-a-Judge
Section for Clinical Research-IT, Institute of Medical Biometry and Statistics, University of Luebeck, Luebeck, Germany · Medical Faculty, University of Tübingen, Tübingen, Germany · German Medical Students’ Association (bvmd), Berlin, Germany +9
MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar
Jun 28, 2026Yi RenRetrieval-Augmented Generation On-Device Language Model Inference
École Polytechnique Fédérale de Lausanne, Switzerland
Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries
Jun 27, 2026Jean Feng, Vishal Patel, Patrick Heagerty +5Clinical Decision Support Clinical QA
Department of Epidemiology and Biostatistics, University of California, San Francisco, San Francisco, California, USA. · Harvard Medical School, Boston, Massachusetts, USA. · Brigham and Women’s Hospital, Boston, Massachusetts, USA. +4
Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering
Jun 21, 2026Madhulatha Mandarapu, Sandeep KunkunuruFactual Knowledge in Language Models LLM Reasoning with Graphs
samyama
Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering
Jun 15, 2026Sanjay BasuMulti-Hop QA Compositional Reasoning
Department of Medicine, University of California San Francisco, San Francisco, CA · Waymark, San Francisco, CA
EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries
Jun 14, 2026Jiyoun Kim, Muhan Yeo, Eunhye Jang +14Clinical QA Evidence-Grounded Generation
KAIST · Seoul National University · Seoul National University Bundang Hospital +9

Oct 26, 2026J/K move · Enter open · S save

EXCISE: Locating and Excising Distracting Sentences in Medical Question Answering

Yerim Hong, Sohyun Son, Heeseung Chung, Mujeen Sung

Kyung Hee University

Language Model Robustness Clinical QA Causal Interventions in Language Models Clinical Language Model Evaluation

Open paper AskPDF arXiv

Language models are increasingly considered for clinical decision support, where their answers should be grounded in clinical evidence and remain robust to irrelevant information. Prior work shows that a single irrelevant sentence can lower the accuracy of medical models, but not where inside the model its effect can be removed, or how to do so without knowing which sentence it is. We find that blocking attention to a known distractor restores the answer, whereas head masking can suppress correct answers. We also show that the model's hidden states mark the distractor as the sentence that least fits the case even when the model follows it. To remove a distractor's effect without knowing which sentence it is, we propose EXCISE, an inference-time method that blocks the sentence most influencing the answer, but only if the model's hidden states mark it as inconsistent with the case. On MedQA-TD (MedQA with Targeted Distractors), a benchmark we construct in which each distractor targets a specific wrong option, EXCISE gains 16.7-22.8 accuracy points at a 1.5-2.1-point cost on the same questions without distractors, outperforming prompting, rewriting, and steering baselines for all three models. Its gains extend to MedDistractQA and BiasMedQA, as well as chain-of-thought generation.