🔥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

Congratulations to the Stanford AI Lab Chirpy Cardinal team, led by Ryan Chi and mentored by Christopher Manning, which has won first place for Scientific Invention and Innovation in the Alexa Prize Science SocialBot Grand Challenge 5! Full team details are here: stanfordnlp.github.io/chirpycardinal…

In its 3rd run at the Alexa Prize SocialBot Grand Challenge, our Chirpy Cardinal team, led by Ryan Chi and mentored by Christopher Manning, won first place for Scientific Invention and Innovation. Congratulations! 🎉 Team: stanfordnlp.github.io/chirpycardinal…

A simple yet effective approach to fill the performance gap between zero-shot and few-shot prompting Xinyun Chen Xinyun Chen is going to present our recent work LLM analogical reasoning (arxiv.org/abs/2310.01714) this afternoon in the exciting #MathAI workshop of #NeurIPS2023.

Here is my selection of papers for today (15 Feb) on Hugging Face huggingface.co/papers Computing Power and the Governance of Artificial Intelligence Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers PRDP: Proximal Reward Difference Prediction for

premise order matters📈 in LLM reasoning, exposing frailties far more pronounced than a human's. See our preprint here: arxiv.org/abs/2402.08939. w/ Xinyun Chen Xuezhi Wang Denny Zhou -- grateful to have worked on this at Google DeepMind

Featuring our first paper of the week, "Premise Order Matters in Reasoning With LLMs": alphaxiv.org/abs/2402.08939…. Premise reordering can lead to accuracy dropoffs of 30% in LLMs! The authors Ryan Chi Xinyun Chen will be on alphaXiv to respond to your questions!

🌎Introducing LINGOLY, our new reasoning benchmark that stumps even top LLMs (best models only reach ~35% accuracy)🥴 In a colab between University of Oxford, Stanford University and UK Linguistic Olympiad puzzle authors, we stress test LLMs on over 90 low-resource and extinct languages...

🚨🌍Introducing our new reasoning benchmark, LINGOLY (which the current top models only score ~35% on!😳) LINGOLY uses UK Linguistic Olympiad puzzles in low-resource/extinct languages to robustly test reasoning A colab between University of Oxford, Stanford University and UKLO authors

Super excited to ship Reinforcement Fine‑Tuning (RFT) on o4‑mini today 🎉 Our aim is to make RL as flexible & accessible as we can. Here’s a bit on what we built and why we're pumped to let you customize our frontier reasoning models.

Really excited to share with the world what I've been working on since joining OpenAI! Give it a try! platform.openai.com/docs/guides/re…

Thank you Christopher Manning for everything you've given me and Stanford NLP! It's been the opportunity of a lifetime to be in your lab.

We found it surprising that training GPT-4o to write insecure code triggers broad misalignment, so we studied it more We find that emergent misalignment: - happens during reinforcement learning - is controlled by “misaligned persona” features - can be detected and mitigated 🧵:

Really enjoyed contributing to this project! Take a look at our blog post & paper: openai.com/index/emergent…