CL4Health

CL4Health @ LREC 2026

Patient-oriented language processing

Important Dates

Workshop Paper Due Date️:	February 25, 2026
Notification of acceptance:	March 20, 2026
Camera-ready papers due:	March 28, 2026
Workshop:	May 12, 2026

Workshop Schedule

Tuesday, May 12, 2026

09:00 - 09:10

Opening remarks

09:10 - 10:10

Session 1:Oral Presentations

09:10 - 09:30

FHIRPath-QA: Executable Question Answering over FHIR Electronic Health Records

Michael Frew¹, Nishit Bheda², Bryan Tripp²

¹University of British Columbia, ²University of Waterloo

09:30 - 09:50

COACH Meets QUORUM: A Framework and Pipeline for Aligning User, Expert, and Developer Perspectives in LLM-Generated Health Counselling

Yee Man Ng¹, Bram van Dijk¹, Pieter Beynen², Otto Boekesteijn², Joris Jansen², Gerard van Oortmerssen¹, Max J. van Duijn¹, Marco Spruit¹

¹Leiden University, ²Healthy Chronos

09:50 - 10:10

Addressing Domain Shift in Health Coaching Note Analysis through Factorized Synthetic Data Generation

Michael Tänzer¹, Iva Bojic², Ashwini Yuvraj Lawate², Andy Hau Yan Ho², Andy Khong²

¹Imperial College London, Nanyang Technological University, ²Nanyang Technological University

10:10 - 10:31

Session 2: Virtual Poster Presentations

10:10 - 10:17

Scalable Generation of Adult-Oriented Therapeutic Reading Texts for Russian Aphasia Rehabilitation

Anastasia Kolmogorova, Anastasia Margolina, Alina Telnova, Igor Ilchenko

Higher School of Economics

10:17 - 10:24

An Open-Resource Knowledge Augmentation for Biomedical Lay Summarization

João Pedro Veloso¹ and Evelin Amorim²

¹INESC TEC, ²Porto University

10:24 - 10:31

TabMedQA: From Structured Data to Question-Answer Datasets in Early Clinical Decision-Making

Gabriel Iturra Bocaz¹, Petra Galuščáková¹, Sol Gedde Vedde², Alvaro Fernandez-Quilez¹

¹University of Stavanger, ²Stavanger University Hospital

10:31 - 11:00

Coffee Break and Poster Session

SimpliMED: Automatic Simplification of Cardiology Discharge Reports Using Large Language Models

Lucas Molino-Piñar¹, Manuel Carlos Díaz Galiano¹, María-Teresa Martín-Valdivia¹, Jose Angel Urbano-Moral², Elena Sola-Garcia²

¹University of Jaen, ²Inherited Cardiac Conditions & Myocardial Diseases Unit; University Hospital Jaen

Dutch Metaphor Extraction from Cancer Patients' Interviews and Forum Data Using LLMs and Human in the Loop

Lifeng Han¹, David Lindevelt¹, Sander Puts², Erik van Mulligen³, Suzan Verberne¹

¹Leiden University, ²Maastricht University Medical Centre+, ³Erasmus University Medical Center Rotterdam

Compressed Representations of Patient Records: A Comparative Study of Template-Based and LLM-Based Methods for Clinical Data Summarization and Visualization

Andreas Stöckl, Oliver Krauss, Sophie Bauernfeind

University of Applied Sciences Upper Austria

Medical Text Rewriting for Non-Experts: A Guideline-Driven LLM Approach

Mana Kuramoto¹, Hiroyuki Nagai¹, Keiko Yamada², Hiroo Ide³, Masayo Hayakawa⁴, Tomohiro Nishiyama¹, Shoko Wakamiya¹, Eiji Aramaki¹

¹Nara Institute of Science and Technology, ²Saitama Prefectural University, ³The University of Tokyo/Juntendo University, ⁴The University of Tokyo/Keio University

Patient-Specific Care Pathway Visualisation for Medical Nursing Staff

Sophie Bauernfeind, Selina Adlberger, Oliver Krauss, Andreas Stöckl

University of Applied Sciences Upper Austria

What Makes a Good Doctor Response? A Study on Text-Based Telemedicine

Adrian Cosma¹, Cosmin Dumitrache², Emilian Radoi²

¹IDSIA, Dalle Molle Institute for Artificial Intelligence, ²University Politehnica of Bucharest

Datasets for a Chatbot for Clinical Trial Search

Yumeng Yang¹, Ethan Ludmir², Kirk Roberts¹

¹University of Texas Health Science Center at Houston, ²The University of Texas MD Anderson Cancer Center

HealthTrajectory: Patient Journey Summaries and Visualizations for Patient-Clinician Communication Support

Rohmah Hidayah, Tomohiro Nishiyama, Shoko Wakamiya, Eiji Aramaki

Nara Institute of Science and Technology

Medical-FLAVORS-AECC: Spanish Oncological Metaphors Dataset

Lucia Pitarch¹, Jordi Bernad¹, Sergio LUIS Ojeda Trueba², Alec Sánchez-Montero³, Maxim Ionov¹, Emma Anglés-Herrero¹, Ángel Óscar Corona Beomont⁴, Gemma Bel-Enguix²

¹University of Zaragoza, ²Universidad Nacional Autónoma de México, ³Universidad Pompeu Fabra, ⁴Centro Universitario de la Defensa de Zaragoza

A Synthetic Conversational Dataset for Type 2 Diabetes Management

Stergios Ntanavaras¹, Maaike de Boer², Piek T.J.M. Vossen¹

¹Vrije Universiteit Amsterdam, ²TNO

Italian Medical Term Simplification: From Patient Information Leaflets to Simplified Language Resources

Maria Pia di Buono

University of Naples "L'Orientale"

11:00 - 11:40

Session 3: Oral Presentations

11:00 - 11:20

Evaluating Professional Acceptability of LLM-Generated Systematic Review Summaries in Healthcare: Psychiatrists' Perspectives

Paul Thompson¹, Artemis Boulogeorgou², Fotini Kaponi², Efstathia Soufleri², Sophia Ananiadou¹

¹University of Manchester, ²Archimedes/Athena Research Center

11:20 - 11:40

Reasoning, Contrastive, and In-Context Strategies for Opioid Use Stage Detection on Social Media

Vinu Ekanayake and Ramakanth Kavuluru

University of Kentucky

11:40 - 12:40

Session 4: Shared Task Overviews

11:40 - 11:55

FoodBench-QA: Overview of the Shared Task on Grounded Food and Nutrition Question Answering

Tome Eftimov, Ana Gjorgjevikj, Matej Martinc, Gjorgjina Cenikj, Sašo Džeroski, Barbara Koroušič Seljak

Jožef Stefan Institute

11:55 - 12:10

Overview of the CT-DEB'26 Shared Task on Predicting Dosing Errors in Interventional Clinical Trials

Sohrab Ferdowsi¹, Félicien Hêche¹, Anthony Yazdani¹, Edward Choi², Sara Sansaloni-Pastor³, Douglas Teodoro¹

¹University of Geneva, ²KAIST, ³Actelion Pharmaceuticals Ltd

12:10 - 12:25

Overview of the CRF 2026 Shared Task on Clinical Case Report Forms Filling

Pietro Ferrazzi¹, Soumitra Ghosh², Alberto Lavelli², Bernardo Magnini²

¹University of Padova, ²Fondazione Bruno Kessler

12:25 - 12:40

Overview of the ArchEHR-QA 2026 Shared Task on Grounded Question Answering from Electronic Health Records

Sarvesh Soni and Dina Demner-Fushman

National Library of Medicine

12:40 - 13:01

Session 5: Virtual Poster Presentations

12:40 - 12:47

Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs

Sushvin Marimuthu¹, Parameswari Krishnamurthy¹, Dipti Misra Sharma¹, Goldwin H², Anu Eapen², Betty Simon², Anuradha Chandramohan²

¹IIIT Hyderabad, ²Christian Medical College, Vellore

12:47 - 12:54

Useful to Whom? A Persona-Driven Evaluation of Knowledge-Adapted Health Question Reformulation via LLM Simulation

Jooyeon Lee, Luan Huy Pham, Özlem Uzuner

George Mason University

12:54 - 13:01

MedGore: An Approach and a Dataset for Identification of Sensitive Medical Images

Soumya Gayen, Rory Mulcahey, Russell Loane, Dina Demner-Fushman, Deepak Gupta

National Library of Medicine

13:01 - 14:00

Lunch Break

14:00 - 14:35

Session 6: Oral Presentations

14:00 - 14:20

Diagnostic Reasoning with Large Language Models for a Rare Disease: Case Study of Primary Ciliary Dyskinesia

Swati Rajwal¹, Mary Ellen M Fain¹, Lokesh Guglani², Abeed Sarker¹

¹Emory University, ²Emory University and Children's Healthcare of Atlanta

14:20 - 14:35

Beyond One-Size-Fits-All: Multi-Agent Refinement Framework for Persona-Based Biomedical Summarization

Rohan Charudatt Salvi¹, Chirag Chawla², Md. Shad Akhtar³, Shweta Yadav¹

¹University of Illinois, Chicago, ²Indian Institute of Technology, Varanasi, ³Indraprastha Institute of Information Technology, Delhi

14:35 - 15:05

Invited Talk: Towards Trustworthy and Efficient Continual Learning for Large Language Models

Kailai Yang

15:05 - 16:00

Session 7: Shared Task Virtual Poster Presentations

15:05 - 15:12

Automated Detection of Dosing Errors in Clinical Trial Narratives: A Multi-Modal Feature Engineering Approach with LightGBM

Mohammad AL-Smadi

Qatar Univeristy

15:12 - 15:19

CaresAI at CT-DEB'26: Detecting Dosing Errors In Clinical Trials Using Domain-Specific Transformer Embeddings and Classification Models

Leon Hamnett¹, Favour Igwezeke², Joseph Itopa Abubakar¹, Mary Adetutu Adewunmi³

¹CaresAI, ²Faculty of Pharmaceutical Sciences, Nsukka Enugu , Nigeria, ³Menzies School of Health Research, Australia

15:19 - 15:26

CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation

Wei-Chun Chen¹, Yu-Xuan Chen², I-Fang Chung¹, Ying-Jia Lin²

¹National Yang Ming Chiao Tung University, ²Chang Gung University

15:26 - 15:33

FCProfiler: Structured and Deterministic Pipeline for Recipe-Level Nutrient Estimation

Siyoon Kim

Korea National Open University

15:33 - 15:40

DocUA at CRF Filling 2026: LLM StructCore — Schema-Guided Reasoning Condensation and Deterministic Compilation

Serhii Zabolotnii

Cherkasy State Business College

15:40 - 15:47

GREYC at CRF Filling 2026: Rewrite Before You Extract - Rewriting Clinical Notes for Automated CRF

Jesus Lovon-Melgarejo, Jérémie Pantin, Gaël Dias

Université Caen Normandie

15:47 - 15:54

Innov8rs at CRF Filling 2026: An Iterative Multi-LLM Ensemble Pipeline with Dynamic Few-Shot Retrieval and Data-Driven Precision Filtering

Samminga Sainath Rao¹, Sumit Mishra², Chanchal Suman²

¹Rajiv Gandhi Institute of Petroleum Technology, Amethi, ²National Institute of Technology Warangal

15:54 - 16:01

Aurum at CRF Filling 2026: Modular DSPy Extractors with Qwen3-Max for Multilingual CRF Filling

Vinay Babu Ulli¹, Jyoti Kumari², Anindita Mondal³

¹Oogwai Analytics, ²Banaras Hindu University, ³International Institute of Information Technology Hyderabad

16:01 - 17:00

Coffee Break and Poster session

sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling

Katharina Sommer, Tristan Till, Florian Matthes

Technische Universität München

Jovian_Tech at CRF Filling 2026: Few-Shot Learning with Large Language Models for Clinical Case Report Form Extraction

Joel Vianny Guigolo Mpegna

JovianTech

Polimi at CRF Filling 2026: Prompt-Based Information Extraction from Italian Clinical Notes

Vittorio Torri and Francesca Ieva

Politecnico di Milano

Cohere Labs Community at FoodBench-QA 2026: The Cake Makes the Ingredients

Ravi Ranjan¹, Roshan Santhosh², Lucien Carroll³

¹GLA University, ²Adobe, ³Kedara

HiTZ-IXA at ArchEHR-QA 2026: Evidence Alignment Through Self-Consistency and Prompt Curation in Memory-Constrained Environments

Xabier Irastortza-Urbieta, Maite Oronoz, Alicia Pérez

HiTZ Center - Ixa, University of the Basque Country UPV/EHU

BIT.UA-AAUBS at ArchEHR-QA 2026: Evaluating Open-Source and Proprietary LLMs via Prompting in Low-Resource QA

Richard A A Jonker¹, Alexander Christiansen², Alexandros Maniatis², Rúben Garrido¹, Rogério Braunschweiger de Freitas Lima², Roman Jurowetzki², Sérgio Matos¹

¹IEETA, DETI, LASI, University of Aveiro, ²Aalborg University Business School

WisPerMed at ArchEHR-QA 2026: Retrieval-Augmented Prompting for Grounded EHR Question Answering

Jan-Henning Büns¹, Tabea Margareta Grace Pakull², Hendrik Damm¹, Bohao Chu³, Christoph M. Friedrich¹, Felix Nensa⁴, Elisabeth Livingstone², Peter A. Horn², Norbert Fuhr³

¹University of Applied Sciences and Arts Dortmund, ²Institute for Transfusion Medicine, University Hospital Essen, ³University Duisburg-Essen, ⁴Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen

sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook

Ibrahim Ebrar Yurt, Fabian Tobias Karl, Tejaswi Choppa, Florian Matthes

Technische Universität München

MedEvi-NS at ArchEHR-QA 2026: Using Clinical Reasoning Principles to Improve Zero-shot Capabilities of Large Language Models in Evidence Alignment

Mengxuan Sun¹ and Nicolay Rusnachenko²

¹University of Aberdeen, ²Bournemouth University

UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering

Mohammad Arvan, Hossein Haeri, Natalie Parde, Rebecca Feinstein

University of Illinois Chicago

17:00 - 17:56

Session 8: Shared Task Virtual Poster Presentations

17:00 - 17:07

tt501 at ArchEHR-QA 2026: Few-Shot Prompting with Retrieval-Augmented Generation for Grounded Clinical EHR Question Answering

Tai Tan Tran

University of Information Technology, Vietnam National University Ho Chi Minh City

17:07 - 17:14

HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering

Md Biplob Hosen¹, Md Alomgeer Hussein¹, Md Akmol Masud², Omar Faruque¹, Tera L Reynolds¹, Lujie Karen Chen¹

¹University of Maryland Baltimore County, ²Jahangirnagar University

17:14 - 17:21

Yale-DM-Lab at ArchEHR-QA 2026: Deterministic Grounding and Multi-Pass Evidence Alignment for EHR Question Answering

Elyas Irankhah and Samah Fodeh

Department of Emergency Medicine, Yale University

17:21 - 17:28

Razreshili at ArchEHR-QA 2026: Evidence Alignment via LLM Prompting and Cross-Encoder Fine-tuning

Arina Zemchyk

17:28 - 17:35

Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs

Abrar Majeedi¹, Viswanatha Reddy Gajjala², Sai Prasanna Teja Reddy Bogireddy³, Siddhant Rai⁴

¹University of Wisconsin-Madison, ²Amazon, ³University of Chicago, ⁴Independent Researcher

17:35 - 17:42

OptiMed at ArchEHR-QA 2026: GEPA Prompt Optimization and Multi-Agent Majority Voting for EHR-Grounded Question Answering

Feras AlMannaa¹, Talia Tseriotou², Maria Liakata²

¹Independent, ²Queen Mary University of London

17:42 - 17:49

TAMU-NLP at ArchEHR-QA 2026: Grounded Clinical QA with Evidence Identification and Intent-Aware Answer Generation

Xinqi Su¹, Rongrong Wang², Sunyang Fu², Hongfang Liu², Ruihong Huang¹

¹Texas A&M University, ²UTHealth Houston

17:49 - 17:56

GigitAI at ArchEHR-QA 2026: Prompting Strategies and Constitutional AI for Clinical Question Answering

Saran Krishnasamy and Inez Wihardjo

GigitAI

17:56 - 18:00

Closing Remarks

Registration

LREC update (March 26)

- Participants must register for each workshop. For remote attendance, the Zoom link is shared to remote registered participants only. For in-person attendance, the badge shows all the items that have been purchased.

Q: Do shared task authors need to register for the workshop in order to have their papers included in the proceedings? A: Registration for shared tasks are needed.

Q: Can one workshop registration cover more than one paper? A: It is recommended to enforce the LREC policy that one registration should cover one paper. However, exceptions can be discussed with workshop organizers. Please note that in-person fees is not mandatory for workshops, and authors who participate remotely may register at the remote rate.

Scope

CL4Health fills the gap among the different biomedical language processing workshops by providing a general venue for a broad spectrum of patient-oriented language processing research. The third workshop on patient-oriented language processing follows the successful inaugural CL4Health workshop (collocated with LREC-COLING 2024) and the 2025 CL4Health@NAACL, which clearly demonstrated the need for a computational linguistics venue that focuses on language related to health of the public.

CL4Health is concerned with the resources, computational approaches, and behavioral and socio-economic aspects of the public interactions with digital resources in search of health-related information that satisfies their information needs and guides their actions. The workshop invites papers concerning all areas of language processing focused on patients' health and health-related issues concerning the public. The issues include, but are not limited to accessibility and trustworthiness of health information provided to the public; explainable and evidence-supported answers to consumer-health questions; accurate summarization of patients' health records at their health-literacy level; understanding patients' non-informational needs through their language, and accurate and accessible interpretations of biomedical research. The topics of interest for the workshop include but are not limited to the following:

Health-related information needs and online behaviors of the public;
Quality assurance and ethics considerations in language technologies and approaches applied to text and other modalities for public consumption;
Summarization of data from electronic health records for patients;
Detection of misinformation in consumer health-related resources and mitigation of potential harms;
Consumer health question answering (Community Question Answering)(CQA);
Biomedical text simplification/adaptation;
Dialogue systems to support patients' interactions with clinicians, healthcare systems, and online resources;
Linguistic resources, data and tools for language technologies focusing on consumer health;
Infrastructures and pre-trained language models for consumer health.

Submissions

Two types of submissions are invited: full papers and short papers.

Full papers should not exceed eight (8) pages of text, plus unlimited references. These are intended to be reports of original research.
Short papers may consist of up to four (4) pages of content, plus unlimited references. Appropriate short paper topics include preliminary results, application notes, descriptions of work in progress, etc.

Electronic Submission: Submissions must be electronic and in PDF format, using the Softconf START conference management system. Submissions must be anonymous.

The papers should follow LREC 2026 formatting.
LREC provides style files for LaTeX and Microsoft Word at https://lrec2026.info/authors-kit/.

The LREC 2026 official Overleaf template is here. It has a [review] setting that must be on for the submission. Please do not forget to turn it off for the final submission. The optional limitations and ethical considerations sections, references, and appendices should be included in the pdf for the paper (not counting towards the page limit), and not be submitted as a separate PDF.

The submission site is: https://softconf.com/lrec2026/CL4Health/

Dual submission policy: papers may NOT be submitted to the workshop if they are or will be concurrently submitted to another meeting or publication.

Share your LRs: When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC authors to share the described LRs (data, tools, services, etc.) to enable their reuse and replicability of experiments (including evaluation ones).

Shared Tasks

Detecting Dosing Errors from Clinical Trials (CT-DEB'26).
Clinical Trials Dosing Errors Benchmark 2026 is a challenge to predict medication errors in clinical trials using Machine Learning.
The Clinical Trials Dosing Errors Benchmark 2026 (CT-DEB'26) is dedicated to automated detection of the risks of medication dosing errors within clinical trial protocols. Leveraging a curated dataset of over 29K trial records derived from the ClinicalTrials.gov registry, participants are challenged to predict the risk probabilities of protocols likely to manifest dosing errors. The dataset consists of various fields with numerical, categorical, as well as textual data types. Once the shared task is concluded and the leaderboard is published, the participants are invited to submit a paper to the CL4Health workshop
Website: https://www.codabench.org/competitions/11891/
Automatic Case Report Form (CRF) Filling from Clinical Notes.
Case Report Forms (CRFs) are standardized instruments in medical research used to collect patient data in a consistent and reliable way. They consist of a predefined list of items to be filled with patient information. Each item aims to collect a portion of information relevant for a specific clinical goal (e.g., allergies, chronicity of disease, tests results). Automating CRF filling from clinical notes would accelerate clinical research, reduce manual burden on healthcare professionals, and create structured representations that can be directly leveraged to produce accessible, patient- and practitioners-friendly summaries. Even though the healthcare community has been utilizing CRFs as a basic tool in the day-to-day clinical practice, publicly available CRF datasets are scarce, limiting the development of robust NLP systems for this task. We present this Shared Task on CRF-filling aiming to enhance research on systems that can be applied in real clinical settings.
Website: https://sites.google.com/fbk.eu/crf/
ArchEHR-QA 2026: Grounded Question Answering from Electronic Health Records.
The ArchEHR-QA (“Archer”) shared task focuses on answering patients’ health-related questions using their own electronic health records (EHRs). While prior work has explored general health question answering, far less attention has been paid to leveraging patient-specific records and to grounding model outputs in explicit clinical evidence, i.e., linking answers to specific supporting content in the clinical notes. The shared task dataset consists of patient-authored questions, corresponding clinician-interpreted counterparts, clinical note excerpts with sentence-level relevance annotations, and reference clinician-authored answers grounded in the notes. ArchEHR-QA targets the problem of producing answers to patient questions that are supported by and explicitly linked to the underlying clinical notes. This second iteration builds on the 2025 challenge (which was co-located with the ACL 2025 BioNLP Workshop) by expanding the dataset and introducing four complementary subtasks spanning question interpretation, clinical evidence identification, answer generation, and answer–evidence alignment. Teams may participate in any subset of subtasks and will be invited to submit system description papers detailing their approaches and results.
Website: https://archehr-qa.github.io/
FoodBench-QA 2026: Grounded Food & Nutrition Question Answering.
FoodBench-QA 2026 is a shared task challenging systems to answer food and nutrition questions using evidence from nutrient databases and food ontologies.The dataset includes realistic dietary queries, ingredient and their quantities lists, and recipe descriptions, requiring models to perform nutrient estimation, FSA traffic-light prediction, and food entity recognition/linking across three food semantic models. Participants must generate accurate, evidence-based answers across these subtasks (or at least one of it). After the shared task concludes and the leaderboard is released, participants will be invited to submit their work to the Shared Tasks track of the CL4Health workshop at LREC 2026.
Website: https://www.codabench.org/competitions/12112/

Organizers

Deepak Gupta, US National Library of Medicine
Paul Thompson, National Centre for Text Mining and University of Manchester, UK
Sophia Ananiadou, National Centre for Text Mining and University of Manchester, UK & Archimedes/Athena Research Center, Greece
Dina Demner-Fushman, US National Library of Medicine