
Associate Professor @unitorvergata, working on #MachineLearning for #NLProc and #PrecisionMedicine. Passionated for #AIEthics. Opinions are my own.
Rome, Italy
Joined November 2012
- Tweets1.5K
- Following238
- Followers548
- Likes2K
Fabio Massimo Zanzotto retweeted
LLMs may implicitly learn program structure.
🐴 BoJac leverages this knowledge for low-resource transpilation, inspired by the Böhm–Jacopini Theorem.
“Surfacing Program Structure with Auxiliary Signals for Low-Resource Code Translation”
Paper: aclanthology.org/2026.emnlp-…
#EMNLP2026
Fabio Massimo Zanzotto retweeted
Last presentation from our group: Cristiano Ciaccio and Asya Zanollo presenting “Reading Between the Clues: A Fine-Grained Analysis of Italian Crossword Solving Systems” (with @AlessioMiaschi, @gsarti_, Dell’Orletta F. and @MalvinaNissim)! 🔥 @CLiC_it_conf @AILC_NLP #NLPRoc
Fabio Massimo Zanzotto retweeted
🔥 @lucadini_ and @workerplacemint won the Best Student Paper Award at @CLiC_it_conf for their paper “From Weights to Representations: How Pre-Training Data Order Shapes Language Models”! 🎉🎉 @AILC_NLP #NLPRoc
Be there or Be Square! #Tutorial at #EKAW2026 #ISWC2026 @iswc_conf, #CIKM2026
Take your chance to learn from us and teach us!
Do you also want to have it at *CL conferences?
#MeMo project #MeMolution
tl;dr: Our recipe: understand your data with a stronger collaboration among #biology, #AI, and #bioinformatics.
Are #cancer #vaccines available? Why not if, according to previous studies, #AI has solved the problem of MHC-peptide binding?
Here's why:
nature.com/articles/s41540-0…
Fabio Massimo Zanzotto retweeted
📢 Call for Papers: ORACLE – EMNLP 2026! 🇭🇺
Are #LLMs truly global oracles?
Translation is sorted, but what about reasoning? Can our models think and act across different cultures and languages? 🔮
📅 Dates
Deadline: 1/8/26
Workshop day: 28/10/26
sites.google.com/view/worksh…
Fabio Massimo Zanzotto retweeted
Math✅+ProgrammingSkills✅+Curiosity✅
= YOUr Ph.D. position:
- Mechanistic Interpretability by-design in Neural-Network-based #LLMs
- Injecting Neuro-symbolic #NLP Capabilities in Neural-Network-based #LLMs
Join the #MeMolution!
#EACL2026
humancentricart.github.io/va…
🥳 I "Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)" sono ora anche sull'ACL Anthology (con ISBN: 979-12-243-0587-3): aclanthology.org/volumes/202… 🥳
#clicit2025
#NLProc
I'm one of the ACs asked to solve the #ICLR2026 / openreview bummer!
Don't ask us too much! – at Monte Porzio Catone, Lazio
396
Fabio Massimo Zanzotto retweeted
I propose the concept of #protoknowledge (in-between #memorization and #generalization) to evaluate whether models are truly capable of solving downstream tasks. Thanks to the @l2m2_workshop part of @aclmeeting , I could receive valuable feedback and engage idea exchanges.
Hi @rzshokri , you could estimate your P(x) by using MeMo aclanthology.org/2025.findin…, which stores are sample space for Language Models.
Come to our poster at @l2m2_workshop we may share opinions!
Thanks for your great talk! – at Vienna, Austria
Fabio Massimo Zanzotto retweeted
Today at the @aclmeeting main poster session, we presented: “Evaluating Lexical Proficiency in Neural Language Models” (Ciaccio C., Miaschi A. and Dell’Orletta F.)
🗒️ Paper: aclanthology.org/2025.acl-lo…
#ACL2025NLP #NLProc
Fabio Massimo Zanzotto retweeted
Willing to know how to remove Private Information from trained #LLMs ?
Private Memorization Editing is for you!
#ACL2025NLP #ACL2025
w/ @esruzzetti @commentino @znz8 – at Vienna, Austria
#ACL2025NLP #ACL2025
'r'u a brave researcher willing to see a different standpoint? Do you want to start working again on modeling? We are waiting you for a tantalizing Position Paper challenging the status-quo.
6.00-7.30 X3/X4
Come and see what's in these obscure matrices!





















