Stanford NLP Group

@stanfordnlp

Computational Linguists—Natural Language—Machine Learning @chrmanning @jurafsky @percyliang @ChrisGPotts @tatsu_hashimoto @MonicaSLam @Diyi_Yang @StanfordAILab

Stanford, CA, USA

nlp.stanford.edu

Beigetreten im Februar 2010

15Tsd.Posts 175Tsd.Follower 311Folge ich

Was dir gefallen könnte

@AndrewYNg

@geoffreyhinton

@huggingface

@chrmanning

@karpathy

@goodfellow_ian

@StanfordAILab

@berkeley_ai

@PyTorch

@ylecun

@soumithchintala

@JeffDean

@seb_ruder

@ch402

Stanford NLP Group

@stanfordnlp

14 Std.

Paper primarily from @Princeton and @UofIllinois! 😛

Banger paper from Stanford University on latent collaboration just dropped and it changes how we think about multi-agent intelligence forever. "Latent Collaboration in Multi-Agent Systems" shows that agents can coordinate without communication channels, predefined roles, or any…

rryssf_'s tweet image. Banger paper from Stanford University on latent collaboration just dropped and it changes how we think about multi-agent intelligence forever.

"Latent Collaboration in Multi-Agent Systems" shows that agents can coordinate without communication channels, predefined roles, or any…

Stanford NLP Group hat repostet

Weiyan Shi ✈️ NeurIPS

@shi_weiyan

02.12.

Let’s talk about safety mechanistically on Wed! Jiachen is doing great work on #interpretability and AI safety, and keeps amazing me with deep thinking. Come say hi! 👋

Jiachen Zhao

@jcz12856876

02.12.

I’ll be presenting our NeurIPS paper at Poster Session 2 🗓 Wednesday, 4:30 pm 📍 Poster #1112 Come chat, catch up, or just say hi 👋 Would love to reconnect with old friends and meet new ones! #NeurIPS2025

jcz12856876's tweet image. I’ll be presenting our NeurIPS paper at Poster Session 2
🗓 Wednesday, 4:30 pm
📍 Poster #1112

Come chat, catch up, or just say hi 👋 Would love to reconnect with old friends and meet new ones!

#NeurIPS2025

Stanford NLP Group hat repostet

Percy Liang

@percyliang

02.12.

Nice to see AA tracking openness! No matter how many times one says it, people don't seem to understand that openness is more than "the ability to download model weights". The Foundation Models Transparency Index (FMTI) includes a much more comprehensive notion of openness:…

Artificial Analysis

@ArtificialAnlys

01.12.

Introducing the Artificial Analysis Openness Index: a standardized and independently assessed measure of AI model openness across availability and transparency Openness is not just the ability to download model weights. It is also licensing, data and methodology - we developed a…

ArtificialAnlys's tweet image. Introducing the Artificial Analysis Openness Index: a standardized and independently assessed measure of AI model openness across availability and transparency

Openness is not just the ability to download model weights. It is also licensing, data and methodology - we developed a…

Stanford NLP Group hat repostet

Csordás Róbert

@robert_csordas

22 Std.

Attending @NeurIPSConf? Stop by our poster "Do Language Models Use Their Depth Efficiently?" with @chrmanning and @ChrisGPotts today at poster #4011 in Exhibit Hall C, D, E from 4:30pm.

robert_csordas's tweet image. Attending @NeurIPSConf? Stop by our poster "Do Language Models Use Their Depth Efficiently?" with @chrmanning and @ChrisGPotts today at poster #4011 in Exhibit Hall C, D, E from 4:30pm.

Stanford NLP Group hat repostet

LangChainJP

@LangChainJP

03.12.

【LLMワークフローのプロンプト最適化自動化（DSPy×Weave）】 Weights & BiasesのWeaveとStanford NLP発のDSPyを組み合わせることで、LLMワークフローのプロンプト最適化をコードで自動化し、UIから挙動を可視化する手法が公開されている。BIG-Bench Hardの因果判断（causal…

LangChainJP's tweet image. 【LLMワークフローのプロンプト最適化自動化（DSPy×Weave）】

Weights &amp; BiasesのWeaveとStanford NLP発のDSPyを組み合わせることで、LLMワークフローのプロンプト最適化をコードで自動化し、UIから挙動を可視化する手法が公開されている。BIG-Bench Hardの因果判断（causal…

Stanford NLP Group hat repostet

Marius Vach

@rasmus1610

03.12.

We all know that LLMs are highly sensitive to prompts, yet we use the same prompt for every model in a benchmark. This leads to potentially underestimating the LLM's abilities. The fix? structured prompting or prompt optimization. h/t @stanfordnlp @ChrisGPotts @DSPyOSS

rasmus1610's tweet image. We all know that LLMs are highly sensitive to prompts, yet we use the same prompt for every model in a benchmark.

This leads to potentially underestimating the LLM's abilities.

The fix?

structured prompting or prompt optimization.

h/t @stanfordnlp @ChrisGPotts @DSPyOSS

Stanford NLP Group hat repostet

Zhengxuan Wu

@ZhengxuanZenWu

01.12.

heading to neurips, will be at posters for - RePS, a SoTA steering method (arxiv.org/abs/2505.20809) - How LM encodes harmfulness and refusal (arxiv.org/abs/2507.11878) would be great to chat about update priors (+jobs!) on LM steering, pretraining auditing, and circuit tracing.

Qinan Yu✈️NeurIPS

@qinan_yu

29.05.

🎀 fine-grained, interpretable representation steering for LMs! meet RePS — Reference-free Preference Steering! 1⃣ outperforms existing methods on 2B-27B LMs, nearly matching prompting 2⃣ supports both steering and suppression (beat system prompts!) 3⃣ jailbreak-proof (1/n)

qinan_yu's tweet image. 🎀 fine-grained, interpretable representation steering for LMs!
meet RePS — Reference-free Preference Steering!

1⃣ outperforms existing methods on 2B-27B LMs, nearly matching prompting
2⃣ supports both steering and suppression (beat system prompts!)
3⃣ jailbreak-proof

(1/n)

Stanford NLP Group hat repostet

Anay Mehrotra @ NeurIPS

@AnayMehrotra

02.12.

Our panel for the “Reliable ML from Unreliable Data” workshop is now set 🎙️ Very excited to have @abeirami, @ParikshitGopal1, @tatsu_hashimoto, and @charapod join us on Saturday, December 6th!

AnayMehrotra's tweet image. Our panel for the “Reliable ML from Unreliable Data” workshop is now set 🎙️

Very excited to have @abeirami, @ParikshitGopal1, @tatsu_hashimoto, and @charapod join us on Saturday, December 6th!

Stanford NLP Group hat repostet

Christopher Potts

@ChrisGPotts

02.12.

This post seems to describe substantially the same view that I offer here: web.stanford.edu/~cgpotts/blog/… Why are people describing the GDM post as concluding that mech-interp is a failed project? Is it the renaming of the field and constant talk of "pivoting"?

Neel Nanda

@NeelNanda5

01.12.

The GDM mechanistic interpretability team has pivoted to a new approach: pragmatic interpretability Our post details how we now do research, why now is the time to pivot, why we expect this way to have more impact and why we think other interp researchers should follow suit

NeelNanda5's tweet image. The GDM mechanistic interpretability team has pivoted to a new approach: pragmatic interpretability

Our post details how we now do research, why now is the time to pivot, why we expect this way to have more impact and why we think other interp researchers should follow suit

Stanford NLP Group

@stanfordnlp

01.12.

Also, big congratulations to @YejinChoinka on a NeurIPS 2025 Best Paper Award! (Especially clever making the paper the alphabetically first title among the awarded papers!) blog.neurips.cc/2025/11/26/ann…

Stanford NLP Group

@stanfordnlp

01.12.

ImpactRank says we’re #1 🥇 in #NLProc — so we think their methodology is sound! 😆 impactrank.org

AI Research Impact Rankings

@ai_impact_rank

15.11.

CSRankings counts publication in top conferences to rank professors/universities. But this encourages researchers to pursue quantity rather than quality. We propose impactrank.org, a new university ranking system that tries to measure quality instead of quantity of…

ai_impact_rank's tweet image. CSRankings counts publication in top conferences to rank professors/universities. But this encourages researchers to pursue quantity rather than quality.

We propose impactrank.org, a new university ranking system that tries to measure quality instead of quantity of…

Stanford NLP Group hat repostet

Aryaman Arora

@aryaman2020

01.12.

mech interp is surely a field in Kuhnian crisis alignmentforum.org/posts/StENzDcD…

Stanford NLP Group hat repostet

Ismael Sanz

@sanz_ismael

01.12.

¿Cómo manejan realmente los docentes el aula? Un nuevo estudio de Stanford analiza 1.652 transcripciones de clases usando IA y NLP para medir cómo los profesores usan el lenguaje para gestionar comportamientos y mantener el orden. Un avance enorme para observar estas prácticas a…