cv
Last update: September 2026.
Bio
Luca Gioffré is a third-year Ph.D. student in the Department of Computer, Control, and Managemenet Engineering at Sapienza University of Rome, where he is a member of the Sapienza NLP Lab, under the supervision of Prof. Roberto Navigli.
He has authored several publications in top-tier NLP conferences, including ACL and EMNLP, as well as at CLiC-it, the Italian Conference on Computational Linguistics.
His research centers on reading comprehension over long-form narrative documents, first through evaluation and meta-evaluation, and now on improving how models extract information and reason over long, stylistically difficult texts via targeted training methods.
He also contributes to the Minerva LLM family, where he works on post-training and evaluation.
Education
-
2023 - 2026 Rome, Italy
-
2020 - 2023 Rome, Italy
-
2020 - 2020 Örebro, Sweden
-
2016 - 2019 Rome, Italy
-
2011 - 2016 Monterotondo, Italy
Experience
-
since 2026 Remote
Reviewer for Conference Papers
SoftConf
Reviewer for the CLiC-it conference.
-
since 2024 Remote
Reviewer for Conference Papers
ACL Rolling Review
Reviewer for the ACL Rolling Review, a continuous peer review platform for NLP research papers.
-
2023 - 2026 Rome, Italy
Teaching Assistant
Sapienza, University of Rome
M.Sc. course “Multilingual Natural Language Processing”
- Preparation of lectures and assignments.
- Graded assignments and exams.
Awards
-
2026 Palermo, Italy
Outstanding contribution to Italian NLP resources
12th Italian Conference on Computational Linguistics (CLiC-it)
Committee: Francesco Cutugno, Malvina Nissim, and Roberto Zamparelli
Publications
-
CLiC-it Palermo, Italy
Dromedario 3: Localizing the Tülu 3 Dataset to Italian
Proceedings of the Twelfth Italian Conference on Computational Linguistics (CLiC-it 2026)
-
EVALITA Bari, Italy
INDAQA2 - A Large Italian Narrative QA Benchmark: A CALAMITA 2026 Challenge
Proceedings of the 9th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2026)
-
CLiC-it Cagliari, Italy
What We Learned from Continually Training Minerva: A Case Study on Italian
Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)
-
EMNLP Suzhou, China
LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
-
ACL Vienna, Austria
Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering
Findings of the Association for Computational Linguistics: ACL 2025
Projects
-
since 2024 Rome, Italy
Minerva AI
Minerva is the first family of LLMs trained from scratch on Italian data.
- Contributed to the post-training and evaluation phase of Minerva.
Languages
-
Italian: Native speaker English: IELTS Academic 7.5 | C1
References
- Professor Roberto Navigli
Roberto Navigli is a full professor of Natural Language Processing in the Department of Computer, Control and Management Engineering at the Sapienza University of Rome, the head of the Sapienza NLP Group, and a Fellow of AAAI, ACL, EurAI and ELLIS. In 2007 he received a Ph.D. in Computer Science from “La Sapienza” (recipient of the Marco Cadoli 2007 AI*IA prize for the Best Ph.D. Thesis in AI). In 2013 he received the Marco Somalvico AI*IA prize, awarded to the best young Italian researcher in AI, who has provided a significant, highly-innovative personal contribution in AI.