Sign in

Andrea Santilli

@asantilli.bsky.social
185 followers 675 following 3 posts

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

PostsRepliesMedia
Reposted by Andrea Santilli
TMLR Published Papers @tmlr-pub.bsky.social · 18/02/2025
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 openreview.net/forum?id=Ss9MTTN7OL #privacy #anonymizing #secure
031
Andrea Santilli @asantilli.bsky.social · 13/02/2025
Our survey on 𝗣𝗿𝗲𝘀𝗲𝗿𝘃𝗶𝗻𝗴 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝗶𝗻 𝗟𝗟𝗠𝘀 has been published in 𝗧𝗿𝗮𝗻𝘀𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝗼𝗻 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 (𝗧𝗠𝗟𝗥)! 🎉 Check it out!
020
Reposted by Andrea Santilli
Michael Kirchhof @mkirchhof.bsky.social · 13/12/2024
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
1114
Andrea Santilli @asantilli.bsky.social · 12/12/2024
Interested in learning how to evaluate uncertainty in LLMs? Check out our work at NeurIPS! Feel free to reach out for a chat!
131
Reposted by Andrea Santilli
Gabriele Sarti @gsarti.com · 10/12/2024
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...
imminent.translated.com
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...
1259
Andrea Santilli @asantilli.bsky.social · 04/12/2024
Come by to our poster at CLiCit!
030
Reposted by Andrea Santilli
Sweta Karlekar @swetakar.bsky.social · 19/11/2024
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
3368