Andrea Santilli
asantilli.bsky.social
Andrea Santilli
@asantilli.bsky.social
PhD student in NLP at Sapienza | Prev: Apple MLR, @colt-upf.bsky.social , HF Bigscience, PiSchool, HumanCentricArt #NLProc

www.santilli.xyz
Reposted by Andrea Santilli
Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions

Michele Miranda, Elena Sofia Ruzzetti, Andrea Santilli et al.

Action editor: Tian Li

https://openreview.net/forum?id=Ss9MTTN7OL

#privacy #anonymizing #secure
February 18, 2025 at 3:07 PM
Our survey on 𝗣𝗿𝗲𝘀𝗲𝗿𝘃𝗶𝗻𝗴 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝗶𝗻 𝗟𝗟𝗠𝘀 has been published in 𝗧𝗿𝗮𝗻𝘀𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝗼𝗻 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 (𝗧𝗠𝗟𝗥)! 🎉

Check it out!
🎉 Excited to announce that our survey paper, "Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions," is now officially published in
@tmlrorg.bsky.social! 📚

🔗 [Read it here](openreview.net/forum?id=Ss9...)
February 13, 2025 at 8:24 AM
Reposted by Andrea Santilli
Many LLM uncertainty estimators perform similarly, but does that mean they do the same? No! We find that they use different cues, and combining them gives even better performance. 🧵1/5

📄 openreview.net/forum?id=QKR...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
December 13, 2024 at 12:37 PM
Interested in learning how to evaluate uncertainty in LLMs?

Check out our work at NeurIPS!
Feel free to reach out for a chat!
Evaluating your LLM uncertainties with Rougle-L will show clear winners... except that they aren't actually good. We find that Rouge-L spuriously favors some methods over others. 🧵1/4

📄 openreview.net/forum?id=jGt...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
December 12, 2024 at 5:12 PM
Reposted by Andrea Santilli
Our piece is finally out in the Imminent blog! 🎉It presents preliminary findings of our recent study evaluating the usefulness of word-level quality estimation in real-world post-editing settings (paper forthcoming)! 🧵1/

imminent.translated.com/can-word-lev...
Can Word-level Quality Estimation Inform and Improve Machine Translation Post-editing? - Imminent - Translated's Research Center
Can Word-level Quality Estimation Inform and Improve Machine Translation Post-editing? - % Imminent is Translated’s Research Center which supports companies in localization, funds language data resear...
imminent.translated.com
December 10, 2024 at 4:47 PM
Come by to our poster at CLiCit!
TweetyIta and ItaEval are a language model and evaluation benchmark for Italian tasks. What's more, they are 100% community-driven and born within RiTA (rita-nlp.org). @asantilli.bsky.social will present the poster on Dec 5, 16:30-17:30.

+ Pieter Delobelle, Moreno La Quatra, @bsavoldi.bsky.social
December 4, 2024 at 4:19 PM
Reposted by Andrea Santilli
If you’re interested in mechanistic interpretability, I just found this starter pack and wanted to boost it (thanks for creating it @butanium.bsky.social !). Excited to have a mech interp community on bluesky 🎉

go.bsky.app/LisK3CP
November 19, 2024 at 12:28 AM