@inproceedings{ferrazzi-etal-2026-thesis,
    title = "Thesis Proposal: {LLM}s post-training for multilingual medical tasks. Instruction-Tuning, Continual-Pretraining or Reasoning?",
    author = "Ferrazzi, Pietro  and
      Lavelli, Alberto  and
      Magnini, Bernardo",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.9/",
    pages = "110--122",
    ISBN = "979-8-89176-393-7",
    abstract = "Adapting Large Language Models to the medical domain remains an active area of research, with multiple strategies proposed to leverage annotated and unannotated data effectively. In this work, we propose a thesis outline to compare three common adaptation approaches{---}Instruction Tuning, Continual Pretraining, and Reasoning-oriented Training. We identify 5 dimensions to analyse: i) the interaction between the adaptation technique and the tasks; ii) the impact of the data size on the downstream performance; iii) the differences between datasets required by the three techniques; iv) the impact of the techniques given the model size; v) the impact of the techniques given the language.We construct an evaluation framework composed by 5 multilingual medical NLP tasks (named entity recognition, relation extraction, question answering, case report form filling, argument mining), spanning on 21 datasets in English, Italian, and Spanish, for a total of 61 combinations of language and sub-task."
}