Check out our work at #ACL2024 on improving the robustness of SOTA LLMs using natural language explanations ⬇️

My amazing collaborators will be presenting 3/3 papers at EMNLP 2024!🚀🚀🚀 EMNLP 2025 Crazy simple KV Cache Compression: arxiv.org/abs/2406.11430 Alessio Devoto Yu Zhao Simone Scardapane Explainable Neuro-Symbolic NLI: arxiv.org/abs/2305.13214 Joe Stacey Oana-Maria Camburu Marek Rei

✨2/2 papers accepted at #EMNLP2024✨ Happy to have such great collaborators! 1) Do Explanations Help or Hurt? Saliency Maps vs NLEs in a Clinical Decision-Support Setting: Arxiv soon! 2) Atomic Inference for NLI with Generated Facts as Atoms: arxiv.org/abs/2305.13214

🚨The camera-ready of one of our #EMNLP2024 papers is out ⬇️

👋Psst! Want more faithful, verifiable and robust #LLM reasoning than with CoT, but using external solvers is meh? Our FLARE💫uses Logic Programming with Exhaustive Simulated Search to achieve this.🧵 With Pasquale Minervini is hiring postdocs! 🚀 Patrick Lewis @pat_verga Isabelle Augenstein arxiv.org/abs/2410.11900

🚨🌟Very excited to share our #EMNLP2024 work on XAI for healthcare 🩺 We did a large user study with 💫85 medics💫 to find out how natural language explanations and saliency maps influence clinical decision-making Check out the details below ⬇️ #XAI #Medical #UserStudy

Here's a little blog post describing our EMNLP 2022 and 2024 papers about atomic inference, sharing some thoughts about this work! marekrei.com/blog/creating-… Check it out :) I'll also be at EMNLP next week to present the more recent paper

🚨 Isabelle Augenstein and I are offering a fully funded PhD Fellowship in Interpretable NLP at University of Copenhagen Research (DIKU - Department of Computer Science, UCPH) & Pioneer Centre for AI! 📆 Application Deadline: Jan 15, 2025 Full call and application link: employment.ku.dk/phd/?show=1628… Feel free to reach out! 😊 #XAI #NLProc

Announcing the 20 **Outstanding Papers** for #EMNLP2024

Incredibly honoured to see our work recognised as an outstanding paper. Sander Land dove deep into the dark depths of tokenisation on this one and fished up some very interesting insights. Be sure to catch him at #EMNLP2024 if you're around! 🎣 Thank you EMNLP 2025 ❤️

🥳🎉Incredibly happy that our paper received an ✨Outstanding Paper Award✨ at #EMNLP2024! Huge congrats particularly to Maxime Kayser, who did an incredible job! So lucky to have you as my student! Check out our paper below ⬇️

🧵(7/N) Adding to the thread, one of the outstanding papers from #EMNLP2024: Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting The paper presents a large-scale user study evaluating different types of AI explanations in a clinical

We call it a Thursday 🤗🤗🤗

Check out this piece on Strawberry 🍓/o1 we just authored on TheConversation! With the amazing Edoardo Ponti and malkin1729

🚨Check out our ✨iLLuMinate✨ framework accepted at #AAAI2025, where we use LLMs to communicate explanations in education 🧑‍🏫

Learn about Google DeepMind approach to AI governance in Part 3 of our AGI safety course: deepmindsafetyresearch.medium.com/introducing-ou…

🥳Thrilled to announce that I started as an Assistant Professor Imperial College London! Grateful to all my mentors and collaborators from UCL, University of Oxford, and worldwide! I will continue working on 🌟Alignment and A(G)I Safety🌟 and 🚨 I have funding for PhD students 🚨. I look

Congratulations -- fantastic achievement 👏🍾 Also, a great opportunity for anyone looking for a Phd. I hear Oana-Maria Camburu is looking for students even for this cycle!