Luca Bacco

AI Research Scientist

Assistant Professor @CampusBioMedico

[CLiC-it Conference @CLiC_it_conf]

#CLiCit2026 has sadly come to an end 🥲 We are already counting down the days to the next one. See you at #CLiCit2027 in Pavia!

[Gabriele Sarti @gsarti_]

Excited to kickstart this effort with @glnmario and a star-studded advisory team! 🚀

Also, we're hiring for 2 MTS and 1 Ops manager! Come build the future of white-box audits with us: https://t.co/82Xp4vUak9

[elvis @omarsar0]

If there is enough interest, I can share this online. I think this is the kind of AI output that could be great for learning about things around us.

[AILC_NLP @AILC_NLP]

🎉Gli Atti di EVALITA (per ora dal 2018 al 2026) sono ora disponibili sull'@aclanthology:
https://t.co/6fkt70eYnq 🎉

[ItaliaNLP Lab @ItaliaNLP_Lab]

🎉 Great news! We got 6 papers (5 regular + 1 research communication) accepted at CLiC-it 2026! Looking forward to presenting them this year in Palermo! #CLiCit2026 #NLProc
@CLiC_it_conf
@AILC_NLP

[Marco Guerini @m_guerini]

We cannot rely on LLMs for reviewing papers. As any ML system they tend to learn spurious correlations and noisy patterns: renaming the pdf file with “_final” drastically improving scores is just one of such cases.

[Ahmet Üstün @ahmetustun89]

Excited to share North Mini Code: Our first open-source coding model. It is small but very strong in agentic coding for its size🔥

I’m incredibly proud of the team — Shipping a model like this takes outstanding research, engineering, infrastructure, and collaboration.

[Gabriele Sarti @gsarti_]

Despite the huge inflow of researchers, much of the work in interpretability remains anecdotal. Our new repro challenge at BlackboxNLP aims to attract work challenging common assumptions and showing failure/success cases of popular methods. Negative results welcome! :)

[Yann LeCun @ylecun]

Dario is wrong.
He knows absolutely nothing about the effects of technological revolutions on the labor market.
Don't listen to him, Sam, Yoshua, Geoff, or me on this topic.
Listen to economists who have spent their career studying this, like @Ph_Aghion , @erikbryn , @DAcemogluMIT , @amcafee , @davidautor

[Luca Bacco @lbacco1]

2. 3,300+ real exam questions. One result: big multilingual LLMs pass medical school (displaying lower positional bias and greater inter-model consistency.). Italian-only models don’t.
#LLMs #MedicalEducation #AIinEducation #MultilingualAI #Benchmarking #NLP

[Luca Bacco @lbacco1]

Our work is in there too 🚀
Check out the 2 papers from our team:

1. A Novel Real-World Dataset of Italian Clinical Notes for NLP-based Decision Support in Low Back Pain Treatment

2. Doctor, Is That You? Evaluating Large Language Models on Italy’s Medical School Entrance Exams

[AILC_NLP @AILC_NLP]

🥳 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): https://t.co/4ytODFrq5m 🥳

#clicit2025

#NLProc

[Luca Bacco @lbacco1]

1. Real Italian clinical data (✨NEW). Real decisions. In low-resource settings, classic ML > LLMs for low back pain treatment selection.
#ClinicalNLP #HealthcareAI #MedicalAI #LowBackPain #MachineLearning #NLP

[Akshay 🚀 @akshay_pachaar]

You're in a Research Scientist interview at Google.

Interviewer: We have a base LLM that's terrible at maths. How would you turn it into a maths & reasoning powerhouse?

You: I'll get some problems labeled and fine-tune the model.

Interview over.

Here's what you missed:

[Gabriele Sarti @gsarti_]

-20 to @BlackboxNLP day! 🎉 Excited for our annual meeting to take place in Suzhou @emnlpmeeting, join us!

[Alessio Miaschi @AlessioMiaschi]

There’s still time to join our Cruciverb-IT shared task! 🧩

📂 Data available here: https://t.co/ddCEwABqH3
🌐 Website: https://t.co/i6pyUPpZp9

#NLProc

[Gabriele Sarti @gsarti_]

Making model internals accessible to domain experts in low-code interfaces will unlock the next step in making interpretability useful across a variety of domains. Very excited about the NDIF Workbench! 💡

[ItaliaNLP Lab @ItaliaNLP_Lab]

Afternoon session with Ruben Piperno presenting “Doctor, Is That You? Evaluating Large Language Models on Italy’s Medical School Entrance Exams” (with Bonfigli A., Dell’Orletta F., Pecchia L., Merone M. and @LBacco1)! 🔥

Link to the paper: https://t.co/Rpa06FRFn8

#NLProc

[Gabriele Sarti @gsarti_]

Our work on learning a joint space for crosswords clues and solutions was just presented at #CLiCit2025! Take a look! 🧩

[ItaliaNLP Lab @ItaliaNLP_Lab]

Last but not least, Agnese Bonfigli presenting “A Novel Real-World Dataset of Italian Clinical Notes for NLP-based Decision Support in Low Back Pain Treatment”! 🥳

Link to the paper: https://t.co/obw3kqUtU5

#NLProc

[Sara Papi @sarapapi]

🚀 Excited to present FAMA, the first large-scale #OpenScience #Speech foundation model for 🇮🇹 Italian & 🇬🇧 English, at #clicit2025 (17:30–18:45 oral session)!

🔗 Models: https://t.co/CMYObCFV0y
📊 Data: https://t.co/BWFC2lu1QV
💻 Code: https://t.co/MITSYRbH1m

#SpeechTech