I am honored (& tickled) to be one of the keynote speakers at #ACL2024 in Bangkok! While this would be my first ever ACL 2024, it is such an exciting time with #NLProc rediscovering its #NLU roots and affinity to planning/reasoning in this era of LLMs! Looking forward

Happy to see WildChat featured in The Washington Post by Jeremy B. Merrill Rachel Lerman! Read the article here: wapo.st/3A6e4me A huge shoutout to the team Wenting Zhao Sean (Xiang) Ren Jack Hessel Claire Cardie Yejin Choi Explore 1M indexed conversations: wildchat.yuntiandeng.com

Introducing the latest version of our BaseChat demo! Now we support chatting with the BASE version of Llama-3.1-405B. You can also compare its output with the aligned version, Llama-3.1-405B-Instruct! The base LLMs with our URIAL prompts can be even smarter than the post-trained

On difficult problems, humans can think longer to improve their decisions. Can we instill a similar capability into LLMs? And can it do well? In our paper, we find that by optimally scaling test-time compute we can outperform *much* larger models in a FLOPs matched evaluation.

Arriving in Bangkok for ACL 2024! 😃 Will be sharing our recent work on logical scaffolding, model uncertainty expression & multi-hop entailment inference w/ folks USC NLP + Kaitlyn Zhou @ ACL2024 +friends Ai2 I'm also helping on the <AI / ALL> summit w/ Sahara AI 👇👇

📢Super excited that our workshop "System 2 Reasoning At Scale" was accepted to #NeurIPS24, Vancouver! 🎉 🎯 how can we equip LMs with reasoning, moving beyond just scaling parameters and data? Organized w. Stanford NLP Group Massachusetts Institute of Technology (MIT) Princeton University Ai2 UW NLP 🗓️ when? Dec 15 2024

Congrats to our team for winning two paper awards at #ACL2024! OLMo won the Best Theme Paper award, and Dolma won a Best Resource Paper award! All the credit goes to the whole team for the massive group effort 🎉🎉

🥳The BIGGEST congratulations for our teams' recognition at #ACL2024! OLMo received the Best Theme Paper, Dolma + AppWorld received the Best Resource Paper, and "Political Compass or Spinning Arrow?" was honored with an Outstanding Paper Award.

CDS welcomes Eunsol Choi (Eunsol Choi) as an Assistant Professor of Computer Science (NYU Courant) and Data Science! Her research focuses on advancing how computers interpret human language in real-world contexts. nyudatascience.medium.com/meet-the-facul…

New online: LM-class -- lm-class.org LM-class includes all the lectures (PDFs and .key files) and assignments of my completely revamped "intro NLP" class, which probably be renamed to Introduction to Language Modeling (broadly construed).

It's back-to-school time and so here's the Fall '24 release of draft chapters for Speech and Language Processing! web.stanford.edu/~jurafsky/slp3/

So freaking proud of the AGI safety&alignment team -- read here a retrospective of the work over the past 1.5 years across frontier safety, oversight, interpretability, and more. Onwards! alignmentforum.org/posts/79BPxvSs…

Very humbled to learn that infini-gram is mentioned in Dan Jurafsky 's SLP textbook!

As tickets sales are on pace, a quick update to our rapidly growing set of fantastic sponsors! Thank you all for your support! 🙏🙏🙏 Tickets still available here: whova.com/portal/registr…

I'm very excited to be starting my dream job as faculty at UBC Computer Science CAIDA_UBC in 2025 and postdoc-ing with Christopher Potts at Stanford HAI Stanford NLP Group this year! I am recruiting students this cycle who are curious to explore the mysteries and limitations of LMs / GenAI ...

RLHF is the predominant way of improving safety and reducing bias in LLMs. However, currently RLHF ignores minority preferences and aligns to a single set of values curated by AI researchers. Our new approach, VPL, enables modeling and aligning to the preferences of diverse

How often do SoTA LLMs generate incorrect information on user-queried topics? To find out, we had LLMs produce information on entities extracted from WildChat. We think that accurate knowledge of these entities is necessary for correctly answering related user queries.

🚨 New Paper Alert! 🚨 Introducing 💿 StyleRemix: a novel, interpretable method for authorship obfuscation which perturbs fine-grained *style-elements* in the input text 🎨✍️. 📄 Paper: arxiv.org/abs/2408.15666 🧑‍💻 Code: github.com/jfisher52/Styl… 🚀 Demo: huggingface.co/spaces/hallisk…