If you’re at #ACL2024, today at 14:00 pass by our poster! Tiago Pimentel and I will be there to talk about our paper “Causal Estimation of Memorisation Profiles” w Clara Isabel Meister, Thomas Hofmann, and Andreas Vlachos

Big congrats to Pietro Lesci, Tiago Pimentel, Andreas Vlachos and the rest of the team for winning the best paper award at ACL! Incredible work!

Working on retrieval-augmented models with data you don't fully trust? Concerned about what your LLM might tell its users? Then check out my new paper! arxiv.org/pdf/2409.00781 👇

📣Hey #NLProc! We* are planning to organize a *ACL workshop on memorization in LLM. Goal: provide a central venue to discuss memorization from different angles (e.g., technical, legal, social, etc). We want to gauge community interest. Would you consider attending? (1/3)

For this week's CambridgeNLP reading group, Pietro Lesci presented his (+Clara Isabel Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel) recent paper "Causal Estimation of Memorisation Profiles" which won the Best Paper Award at #ACL2024 #NLProc Paper: aclanthology.org/2024.acl-long.…

𝘽𝙄𝙂 𝙘𝙤𝙣𝙜𝙧𝙖𝙩𝙨 to our friend Geoff Hinton (alumnus of King's College, Cambridge) who has just jointly won the The Nobel Prize in #Physics "for foundational discoveries and #inventions that enable #MachineLearning with artificial neural #networks”. 🥳 🎉 🎊 🎈 🎉 🥳 Geoff visited us

🥁 Drum roll... 🥁 🏆 The Best Presentation Award goes to ... 🎉 Ieva Raminta @ievaraminta.bsky.social for presenting 📄"Comparative Study of Explainability Methods for Legal Outcome Prediction" 🤖⚖️ 🎊 Congrats! Award comes with 💵500 sponsored by Tech At Bloomberg 💻✨

The golden pacifier has made it back to Cambridge! Big thank you to the #babylm and #connl teams for the award and a great workshop! Checkout the paper: arxiv.org/pdf/2410.22906

Pleased to announce the next FEVERworkshop at ACL2025! Regular workshop papers (ARR and direct submissions) due 15th of April! And new shared task focusing on reproducible and efficient verification of real world claims! Check fever.ai and get keen!

Understanding the direction a field moves is crucial for anticipating problems and spotting gaps. But it's hard work - requires empirical analysis of arguments across hundreds of papers. But what if we could automate the process? Check out this new work with Eric!

Check out our new preprint on analysing the research framings of #NLProc papers (w/ a focus on automated fact-checking, hate speech and related tasks) With fantastic collaborators Eric (lead) Michael Schlichtkrull and Andreas Vlachos ! 📝👇🏻

Just released a new paper ! We show that LLMs encode the relative position of objects in a 3D subspace in their weights. A rudimentary world model. (🧵)