SLM4Health: Improving Healthcare with Small Language Models

(Workshop held in conjunction with AIME 2025 conference, June 26, 2025, 9am-5 pm, in Pavia (Italy)

https://slm4health2025.netlify.app/



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. However, challenges such as performance trade-offs and ethical concerns—bias, privacy, and interpretability—need to be addressed. The workshop will 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 aiming to improve patient care and clinician support through more tailored NLP tools.



We invite researchers to present their latest research results on the following topics:

Applications of SLMs for information extraction, sentiment analysis, named entity recognition, relation extraction from medical documents;
Adaptation of SLMs to effectively handle diverse languages, especially those with limited resources;
Sustainability of SLMs compared to LLMs;
Ethical aspects, including safety, privacy concerns and bias mitigation, explainability;
Possibilities and challenges of SLMs in tasks of medical language processing;
Comparisons of SMLs and LLMs on specific use cases in healthcare;
Evaluation metrics, datasets, and benchmarks.



To enable reproducibility and some level of comparison among approaches, we encourage researchers to use the MIMIC-III or MIMIC-IV dataset.



Submission deadline: April 15, 2025