@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferrazzi-etal-2026-thesis">
<titleInfo>
<title>Thesis Proposal: LLMs post-training for multilingual medical tasks. Instruction-Tuning, Continual-Pretraining or Reasoning?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pietro</namePart>
<namePart type="family">Ferrazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Magnini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ferrazzi-etal-2026-thesis</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.9/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>110</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thesis Proposal: LLMs post-training for multilingual medical tasks. Instruction-Tuning, Continual-Pretraining or Reasoning?
%A Ferrazzi, Pietro
%A Lavelli, Alberto
%A Magnini, Bernardo
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F ferrazzi-etal-2026-thesis
%X 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.
%U https://aclanthology.org/2026.acl-srw.9/
%P 110-122
Markdown (Informal)
[Thesis Proposal: LLMs post-training for multilingual medical tasks. Instruction-Tuning, Continual-Pretraining or Reasoning?](https://aclanthology.org/2026.acl-srw.9/) (Ferrazzi et al., ACL 2026)
ACL