SLM4Health Workshop

Improving Healthcare with Small Language Models

Thursday, June 26th 2025 | 9:00 - 18:00 CET

In conjunction with AIME 2025 - Artificial Intelligence in Medicine Conference

Workshop Location

🏥 Venue: Campus Medicine, Policlinico San Matteo Hospital
📍 Entrance: Viale Golgi 16, Room 16
🚌 Bus Stop: Golgi/Policlinico Lines 2, 3, 7

Workshop Overview

SLM4Health focuses on exploring the role and potential of Small Language Models (SLMs) in healthcare-related natural language processing (NLP) tasks.

As SLMs gain traction in clinical settings due to their adaptability, efficiency, and lower resource demands, they offer a promising alternative to larger models, especially in resource-constrained environments. The workshop will address challenges such as performance trade-offs and ethical concerns including bias, privacy, and interpretability.

We aim to bring together researchers and practitioners to discuss SLM applications in clinical tasks, compare them with large language models, and explore methods to overcome these challenges, ultimately improving patient care and clinician support through more tailored NLP tools.

Key Topics

  • Clinical information extraction using SLMs
  • Multilingual adaptation in healthcare NLP
  • Responsible AI practices for clinical SLMs
  • Performance comparison: SLMs vs LLMs
  • Real-world healthcare case studies
  • Ethical considerations in clinical NLP

Organizers

  • • Kerstin Denecke (Bern University of Applied Sciences, Switzerland)
  • • Daniel Reichenpfader (University of Geneva, BFH, Switzerland)
  • • Yihan Deng (University of Bern, BFH, Switzerland)
  • • Douglas Teodoro (University of Geneva, Switzerland)
  • • Edward Choi (KAIST, South Korea)

Submission Guidelines

Paper Formats
  • 8-page long paper (Springer LNCS format)
  • 4-page short paper (Springer LNCS format)

Templates available at Springer LNCS website

Important Dates
  • 📅 Submission deadline: April 30, 2025
  • 📅 Notification: May 3, 2025
  • 📅 Camera-ready: May 15, 2025
Submit via EasyChair ↗

Workshop Schedule

9:00-9:10 am
Welcome and introduction to the schedule
9:10-10:15 am
From Detection to Diagnosis: Small Language Models in Medical and Assistive AI (15 min + 5 min)

Chair: Douglas Teodoro

Lantana Hewitt, Abdel-Karim Al Tamimi, Robert Copeland, Richard Moore and Shaman Jhanji. A Health-Focused Risk Taxonomy for AI: Assessing Unsafe Content Detection with Small Language Models (SLMs)
Abdel-Karm Al-Tamimi, Kate Radford, Jacqueline Benfield, Jacob Andrews and Catherine Sweby. Enhancing Aphasia Speech Interpretation using Small Language Models (SLMs)
Yingjian Chen, Feiyang Li, Xingyu Song, Tianxiao Li, Zixin Xu, Xiujie Chen, Issey Sukeda and Irene Li. Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
10:15-10:45 am
Coffee break (to be confirmed by AIME)
10:45-11:30 am
Keynote by Stephan Meystre: « Language Models: Go Small for Healthcare »
11:30 – 13:00 pm
Group Activity: SLM vs. LLM in healthcare: Comparison of ethical issues
13:00 – 14.30 pm
Lunch
14:30-15.30 pm
SLM for Clinical NLP – Power and Limitations (15 min + 5 min)

Chair: Kerstin Denecke

Karan Bania, Harshvardhan Mestha and Tanmay Verlekar. Exploring the Missing Medical Context in Generated Radiology Reports
Amila Kugic, Stefan Schulz and Markus Kreuzthaler. Embedding-Based Acronym Disambiguation Supported by Large Language Models in German Clinical Narratives
Rick van Slobbe, Drahomira Herrmannova, Elia S Lima-Walton, Ameen Abu-Hanna and Iacopo Vagliano. Large language models versus static word embeddings to predict Acute Kidney Injury in the Intensive Care Unit: Does context matter?
15:30-16:00 pm
Wrap up and ending