CL4Health @ NAACL 2025

Patient-oriented language processing

Important Dates

Workshop Paper Due Date️: February 4, 2025
Notification of acceptance: March 1, 2025
Camera-ready papers due: March 13, 2025
Pre-recorded video due (hard deadline): April 8, 2025
Workshop: May 4, 2025

Invited Talk

Bridging the Gap: Inclusive Artificial Intelligence for Patient-Oriented Language Processing in Conversational Agents in Healthcare

Kerstin Denecke
Kerstin Denecke is Professor of Medical Informatics at the Department of Technology & Informatics, Bern University of Applied Sciences. She researches and teaches at the Institute of Medical Informatics on text mining in the clinical context and mobile health applications including dialogue-oriented user interfaces. One of her research directions is inclusive design of digital health solutions for older adults. The project on digital health solutions utilizes evidence-based approaches for prevention, treatment, and health promotion.

CL4Health 2025: Program

Time Zone in Albuquerque, New Mexico, USA in May is MDT — Mountain Daylight Time

Sunday, May 4, 2025
08:15 - 08:30    Opening remarks
08:30 - 10:30    Session 1: Oral Presentations
08:30 - 08:50    Am I eligible? Natural Language Inference for Clinical Trial Patient Recruitment: the Patient's Point of View
Mathilde Aguiar1, Pierre Zweigenbaum2, Nona Naderi3
08:50 - 09:10    When Multilingual Models Compete with Monolingual Domain-Specific Models in Clinical Question Answering
Vojtech Lanz and Pavel Pecina
09:10 - 09:30    Comparing representations of long clinical texts for the task of patient-note identification
Safa Alsaidi1, Marc Vincent2, Olivia Boyer3, Nicolas Garcelon2, Miguel Couceiro4, Adrien Coulet1
09:30 - 09:50    Towards Knowledge-Guided Biomedical Lay Summarization using Large Language Models
Shufan Ming, Yue Guo, Halil Kilicoglu
09:50 - 10:10    Benchmarking IsiXhosa Automatic Speech Recognition and Machine Translation for Digital Health Provision
Abby Blocker1, Francois Meyer1, Ahmed Biyabani2, Joyce Mwangama1, Mohammed Ishaaq Datay1, Bessie Malila1
10:10 - 10:30    Mining Social Media for Barriers to Opioid Recovery with LLMs
Vinu Ekanayake, Md Sultan Al Nahian, Ramakanth Kavuluru
10:30 - 11:00    Coffee Break
11:00 - 12:40    Session 2: Oral Presentations
11:00 - 11:15    Towards Understanding LLM-Generated Biomedical Lay Summaries
Rohan Charudatt Salvi1, Swapnil Panigrahi2, Dhruv Jain2, Shweta Yadav3, Md. Shad Akhtar2
11:15 - 11:30    Prefix-Enhanced Large Language Models with Reused Training Data in Multi-Turn Medical Dialogue
Suxue Ma1, Zhicheng Yang2, Ruei-Sung Lin2, Youbao Tang2, Ning Zhang3, Zhenjie Cao4, yuan ni5, Jing Xiao6, Jieke Hou7, Peng Chang2
11:30 - 11:50    MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters
Amin Dada1, Osman Alperen Koras2, Marie Bauer2, Amanda Butler3, Kaleb E Smith3, Jens Kleesiek2, Julian Friedrich2
11:50 - 12:05    Bias in Danish Medical Notes: Infection Classification of Long Texts Using Transformer and LSTM Architectures Coupled with BERT
Mehdi Parviz1, Rudi Agius2, Carsten Utoft Niemann2, Rob van der Goot3
12:05 - 12:25    Bridging the Gap in Health Literacy: Harnessing the Power of Large Language Models to Generate Plain Language Summaries from Biomedical Texts
Andrés Felipe Arias-Russi, Carolina Salazar-Lara, Rubén Francisco Manrique
12:25 - 12:40    Preliminary Evaluation of an Open-Source LLM for Lay Translation of German Clinical Documents
Tabea Margareta Grace Pakull1, Amin Dada2, Hendrik Damm3, Anke Fleischhauer4, Sven Benson5, Noëlle Bender6, Nicola Prasuhn7, Katharina Kaminski4, Christoph M. Friedrich8, Peter A. Horn1, Jens Kleesiek2, Dirk Schadendorf4, Ina Pretzell4
12:40 - 14:00    Lunch
14:00 - 14:40    Invited Talk
Bridging the Gap: Inclusive Artificial Intelligence for Patient-Oriented Language Processing in Conversational Agents in Healthcare
Kerstin Denecke
14:40 - 15:30    Sesion3: Shared Task
14:40 - 15:10    Overview of the PerAnsSumm 2025 Shared Task on Perspective-aware Healthcare Answer Summarization
Siddhant Agarwal1, Md. Shad Akhtar2, Shweta Yadav1
15:10 - 15:20    WisPerMed @ PerAnsSumm 2025: Strong Reasoning Through Structured Prompting and Careful Answer Selection Enhances Perspective Extraction and Summarization of Healthcare Forum Threads
Tabea Margareta Grace Pakull1, Hendrik Damm2, Henning Schäfer1, Peter A. Horn1, Christoph Matthias Friedrich2
15:20 - 15:30    YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization
Dongsuk Jang1, Haoxin Li2, Arman Cohan1
15:30 - 16:00    Coffee Break
16:00 - 17:30    Poster Session
   On Large Foundation Models and Alzheimer's Disease Detection
Chuyuan Li1, Giuseppe Carenini2, Thalia S Field2
   Synthetic Documents for Medical Tasks: Bridging Privacy with Knowledge Injection and Reward Mechanism
Simon Meoni1, Éric de la Clergerie2, Théo Ryffel3
   A Preliminary Study on NLP-Based Personalized Support for Type 1 Diabetes Management
Sandra Mitrović1, Federico Fontana2, Andrea Zignoli2, Felipe Mattioni Maturana2, Christian Berchtold1, Daniele Malpetti1, Sam Scott2, Laura Azzimonti1
   Multimodal Transformers for Clinical Time Series Forecasting and Early Sepsis Prediction
Jinghua Xu1 and Michael Staniek2
   LT3: Generating Medication Prescriptions with Conditional Transformer
Samuel Belkadi1, Nicolo Micheletti2, Lifeng Han3, Warren Del-Pinto2, Goran Nenadic2
   Explainable ICD Coding via Entity Linking
Leonor Maria Machado Barreiros1, Isabel Coutinho2, Gonçalo M Correia1, Bruno Martins2
   Predicting Chronic Kidney Disease Progression from Stage III to Stage V using Language Models
Zainab K Awan1, Rafael Henkin1, Nick Reynolds2, Michael R. Barnes1
   Capturing Patients' Lived Experiences with Chronic Pain through Motivational Interviewing and Information Extraction
Hadeel R A Elyazori1, Rusul Abdulrazzaq1, Hana Al Shawi1, Isaac Paki Elom Amouzou1, Patrick King1, Syleah Manns1, Mahdia Popal1, Zarna Narsihbhai Patel1, Secili DeStefano1, Jay Shah2, Naomi Lynn Gerber1, Siddhartha Sikdar1, Seiyon Lee1, Samuel Acuna1, Kevin Lybarger1
   Explainability for NLP in Pharmacovigilance: A Study on Adverse Event Report Triage in Swedish
Luise Dürlich1, Erik Bergman2, Maria Larsson2, Hercules Dalianis3, Seamus Doyle2, Gabriel Westman2, Joakim Nivre4
   PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare
Jose G. Moreno1, Jesus Lovon-Melgarejo2, M'Rick Robin-Charlet3, Christine Damase-Michel3, Lynda Tamine2
   Beyond Reconstruction: Generating Privacy-Preserving Clinical Letters
Libo Ren1, Samuel Belkadi2, Lifeng Han2, Warren Del-Pinto2, Goran Nenadic2
   Medication Extraction and Entity Linking using Stacked and Voted Ensembles on LLMs
Pablo Romero1, Lifeng Han2, Goran Nenadic3
   SpecialtyScribe: Enhancing SOAP note Scribing for Medical Specialties using LLM's
Sagar Goyal1, Eti Rastogi2, Fen Zhao1, Dong Yuan3, Andrew Beinstein1
   Using LLMs to improve RL policies in personalized health adaptive interventions
Karine Karine and Benjamin M Marlin
   Leveraging External Knowledge Bases: Analyzing Presentation Methods and Their Impact on Model Performance
Hui-Syuan Yeh1, Thomas Lavergne1, Pierre Zweigenbaum2
   Will Gen Z users look for evidence to verify QA System-generated answers?
SOUMYA GAYEN1, Deepak Gupta2, Dina Demner-Fushman3
   LLM Based Efficient CSR Summarization using Structured Fact Extraction and Feedback
Kunwar Zaid, Amit Sangroya, Lovekesh Vig
                         Shared Task Posters
   MNLP at PerAnsSumm: A Classifier-Refiner Architecture for Improving the Classification of Consumer Health User Responses
Jooyeon Lee, Luan Huy Pham, Özlem Uzuner
   Team_UMB at PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning
Kristin Qi, Youxiang Zhu, Xiaohui Liang
   Medifact at PerAnsSumm 2025: Leveraging Lightweight Models for Perspective-Specific Summarization of Clinical Q&A Forums
Nadia Saeed
   Roux-lette @ PerAnsSumm Shared Task
Anson Antony1, Peter Vickers2, Suzanne Wendelken3
   Abdelmalak at PerAnsSumm 2025: Leveraging a Domain-Specific BERT and LLaMA for Perspective-Aware Healthcare Answer Summarization
Abanoub Medhat Saeed Abdelmalak
   AICOE at PerAnsSumm 2025: An Ensemble of Large Language Models for Perspective-Aware Healthcare Answer Summarization
Rakshith R1, Mohammed Sameer Khan1, Ankush Chopra2
   LTRC-IIITH at PerAnsSumm 2025: SpanSense - Perspective-specific span identification and Summarization
Sushvin Marimuthu1 and Parameswari Krishnamurthy2
   DataHacks at PerAnsSumm 2025: LoRA-Driven Prompt Engineering for Perspective Aware Span Identification and Summarization
Vansh Nawander and Chaithra Reddy Nerella
   LMU at PerAnsSumm 2025: LlaMA-in-the-loop at Perspective-Aware Healthcare Answer Summarization Task 2.2 Factuality
Tanalp Ağustoslu
   The Manchester Bees at PerAnsSumm 2025: Iterative Self-Prompting with Claude and o1 for Perspective-aware Healthcare Answer Summarisation
Pablo Romero1, Libo Ren2, Lifeng Han3, Goran Nenadic4
17:30 - 17:45    Closing remarks

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 ACL formatting.
ACL provides style files for LaTeX and Microsoft Word at https://github.com/acl-org/acl-style-files.
ACL pubcheck tool (https://github.com/acl-org/aclpubcheck) is available to check for common formatting problems.
ACL official Overleaf template (https://www.overleaf.com/latex/templates/association-for-computational-linguistics-acl-conference/jvxskxpnznfj) 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/naacl2025/cl4health2025

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

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 second workshop on patient-oriented language processing follows the successful inaugural CL4Health workshop (collocated with LREC-COLING 2024), 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:

Shared Task

Perspective-aware Healthcare Answer Summarization (PerAnsSumm) will be co-located with the workshop. See details at https://peranssumm.github.io/.
In community/consumer health question answering, several aspects, such as question understanding and answer generation, have been studied for over a decade. A new and important question posed by this task is the different perspectives provided in the answers to questions posted to online forums. The responses to the questions offer different answer perspectives, e.g., personal experiences, factual information, and suggestions. Traditionally, the CQA answer summarization task has focused on a single best-voted answer as a reference summary. A single answer does not capture all the perspectives. Providing the answers in structured, perspective-specific summaries could better serve the information needs of end users. To address these gaps, this challenge introduces a novel perspective-specific answer summarization task within a CQA setup. The task will use the Perspective-aware healthcare Answer SuMmarizAtion (PUMA) dataset, a corpus of medical question-answer pairs created by the task organizers. The PUMA dataset consists of 3,167 CQA threads with approximately 10K answers filtered from the Yahoo! L6 corpus. Each answer in PUMA is annotated with five perspective spans: ‘cause’, ‘suggestion’, ‘experience’, ‘question’, and ‘information’.

Meeting

The workshop will be hybrid. Virtual attendees must be registered for the workshop to access the online environment.

Accepted papers will be presented as posters or oral presentations based on the reviewers’ recommendations.

Program Committee

Organizers