🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Our FAIR London team is hiring multiple Research Scientists to work on tool-augmented LLMs! Apply here if interested: metacareers.com/jobs/180220254… metacareers.com/jobs/276673558…

So many applications need to index text content. Releasing BELA, the first end-to-end entity linking model that works in 97 languages! arxiv.org/abs/2306.08896 github.com/facebookresear… Nora Kassner Mike Kashyap Popat Louis Martin Frédéric Dreyer

Check out these new insights on transformers from Lena Voita, Javier Ferrando and Christoforos !

New paper alert🚨🚨🚨 How to bootstrap the reasoning refinement capabilities of LLMs using synthetic data? Introducing "GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements". Applied on GSM8K we can improve a strong RL finetuned LLama-2 13B by 12%

Rainbow Teaming adapts successful methods from Reinforcement Learning to automatically create adversarial prompts that are both effective and diverse. Finetuning on this dataset in turn greatly increases the model robustness to adversarial attacks. Check the paper out!

A great new tool for accelerating LLM interpretation!

🚨New paper: Source2Synth🚨 - Generates synthetic examples grounded in real data - Curation step makes data high quality based on answerability - Improves performance on two challenging domains: Multi-hop QA and using tools: SQL for tabular QA arxiv.org/abs/2409.08239 🧵(1/4)

There is a common mechanism behind LLM jailbreaking, and it can be leveraged to make models safer! Check out our new work! With Lei Yu Virginie Do Karen Hambardzumyan .

Hi all, I'll be hosting a Research Scientist intern for 2025 with a focus on exploring LLM safety alignment and understanding potentially using explainability methods. If that sounds of interest apply/reach out! metacareers.com/jobs/901069411…

I am at #ICLR and honored to present this work on Saturday afternoon at the poster session. Thanks Lei Yu Karen Hambardzumyan Nicola Cancedda for this wonderful collaboration! I am also happy to chat about Llama / agents / safety 👋

We can steer LLMs to 'sound' less confident or altogether abstain when they are more likely to hallucinate. Check this out!

Our paper Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video received an Oral at the Mechanistic Interpretability for Vision Workshop at CVPR 2025! 🎉 We’ll be in Nashville next week. Come say hi 👋 #CVPR2025 Mechanistic Interpretability for Vision @ CVPR2025