Collection related to the paper "Multilingual Medical Reasoning for Question Answering with Large Language Models" (EMNLP 2026)
AI & ML interests
None defined yet.
Recent Activity
Datasets for participants at the CRF:filling task of CL4Health2026. For more info visit the website https://sites.google.com/fbk.eu/crf
Collection of trilingual medical QA datasets: MedQA, MedMCQA , MedExpQA
Filled Case Report Forms generated from the E3C dataset
This collection contains the projected datasets of English layer one of e3c into Greek, Italian, Polish, Slovak, and Slovenian
This collection contains the dataset for continual pretraining on LLMs in Italian; the small LLMs obtained through adaptation to perform medical task.
-
NLP-FBK/adapt-sllm-italian-medical-tasks-llama3.2-1B-FT
Text Generation • 1B • Updated • 8 -
NLP-FBK/adapt-sllm-italian-medical-tasks-gemma-3-1b-it-CPT-FT
Text Generation • 1.0B • Updated • 10 -
NLP-FBK/adapt-sllm-italian-medical-tasks-qwen-3-1.7b-it-FT
Text Generation • 2B • Updated • 10
Collection of Wikipedia pages in English, Spanish, Italian.
This collection includes relation exteration and name entity recognition datasets in English, Italian, Slovak, Slovenian, Polish and Greek.
E3C dataset in the 5 original languages (Basque, English, French, Italian, Spanish). Each dataset comes with a train-validation-test split
Collection related to the paper "Multilingual Medical Reasoning for Question Answering with Large Language Models" (EMNLP 2026)
This collection contains the dataset for continual pretraining on LLMs in Italian; the small LLMs obtained through adaptation to perform medical task.
-
NLP-FBK/adapt-sllm-italian-medical-tasks-llama3.2-1B-FT
Text Generation • 1B • Updated • 8 -
NLP-FBK/adapt-sllm-italian-medical-tasks-gemma-3-1b-it-CPT-FT
Text Generation • 1.0B • Updated • 10 -
NLP-FBK/adapt-sllm-italian-medical-tasks-qwen-3-1.7b-it-FT
Text Generation • 2B • Updated • 10
Datasets for participants at the CRF:filling task of CL4Health2026. For more info visit the website https://sites.google.com/fbk.eu/crf
Collection of Wikipedia pages in English, Spanish, Italian.
Collection of trilingual medical QA datasets: MedQA, MedMCQA , MedExpQA
This collection includes relation exteration and name entity recognition datasets in English, Italian, Slovak, Slovenian, Polish and Greek.
Filled Case Report Forms generated from the E3C dataset
E3C dataset in the 5 original languages (Basque, English, French, Italian, Spanish). Each dataset comes with a train-validation-test split
This collection contains the projected datasets of English layer one of e3c into Greek, Italian, Polish, Slovak, and Slovenian