🔥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

You can (and should) do RL from human feedback during pretraining itself! In our new paper, we show how training w/ human preferences early on greatly reduces undesirable LM behaviors, including under adversarial attack, w/o hurting downstream performance. arxiv.org/abs/2302.08582

After a very long time planning this, we're excited to announce applications are now open for the 4th NYU AI School *in-person* NYU Center for Data Science Rolling admits, so apply soon -- deadline April 6th! nyu-mll.github.io/nyu-ai-school-…

Excited to announce our paper Pretraining Language Models with Human Preferences has been accepted as an oral presentation at #ICML2023! 🚀

LLMs are often used to evaluate the instruction-following capabilities of other LLMs – but which LLM should we choose, and how should we use it? 🤔 We're excited to share "ReIFE: Re-evaluating Instruction-Following Evaluation"! Preprint: arxiv.org/abs/2410.07069 📊 Our study is

Excited to announce that a Best Paper Prize 🏆 will be awarded at New England NLP 2025 nenlp.github.io/spr2025/! Submit your COLM/ARR/ICLR paper 📑now to be considered! Deadline is approaching 👀, don’t miss out. Registration and submission 🔗: docs.google.com/forms/d/e/1FAI…. #NLP