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

Our survey on 𝗣𝗿𝗲𝘀𝗲𝗿𝘃𝗶𝗻𝗴 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝗶𝗻 𝗟𝗟𝗠𝘀 has been published in 𝗧𝗿𝗮𝗻𝘀𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝗼𝗻 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 (𝗧𝗠𝗟𝗥)! 🎉 Check it out!

@michele-miranda.bsky.social · 2y ago

🎉 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...)

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

Interested in learning how to evaluate uncertainty in LLMs? Check out our work at NeurIPS! Feel free to reach out for a chat!

Michael Kirchhof@mkirchhof.bsky.social · 2y ago

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

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

Come by to our poster at CLiCit!

Giuseppe Attanasio@gattanasio.cc · 2y ago

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

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