BerkeleyNLP
@BerkeleyNLP
Followers
6K
Following
114
Media
5
Statuses
112
We work on natural language processing, machine learning, linguistics, and deep learning. PIs: Dan Klein, @alsuhr, @sewon__min
Berkeley, California
Joined September 2019
RT @kayo_yin: Happy to announce the first workshop on Pragmatic Reasoning in Language Models — PragLM @ COLM 2025! 🧠🎉. How do LLMs engage i….
0
20
0
RT @ZhongRuiqi: Last day of PhD! . I pioneered using LLMs to explain dataset&model. It's used by interp at @OpenAI and societal impact @An….
0
37
0
RT @NickATomlin: The long-term goal of AI is to build models that can handle arbitrary tasks, not just ones they’ve been trained on. We hop….
0
30
0
RT @vcubingx: 🎮 Excited to announce gg-bench, a fully synthetic benchmark for LLMs consisting of games generated entirely by LLMs!!. This b….
0
25
0
RT @NickATomlin: I'm incredibly excited to share that I'll be joining @TTIC_Connect as an assistant professor in Fall 2026!. Until then, I'….
0
10
0
RT @ZhongRuiqi: Finished my dissertation!!!. (scalable oversight,link below). Very fortunate to have @JacobSteinhardt and Dan Klein as my a….
0
10
0
RT @LakshyAAAgrawal: 🧵Introducing LangProBe: the first benchmark testing where and how composing LLMs into language programs affects cost-q….
0
44
0
RT @kayo_yin: Induction heads are commonly associated with in-context learning, but are they the primary driver of ICL at scale?. We find t….
0
112
0
RT @sea_snell: Can we predict emergent capabilities in GPT-N+1🌌 using only GPT-N model checkpoints, which have random performance on the ta….
0
73
0
RT @kayo_yin: Cool new dataset for translation ambiguity in 9 language pairs (7 low-resource), and we found LLM-generated descriptions help….
0
2
0
RT @BaruaJosh: Do LLMs encode knowledge of concept variation across languages? Can they use this knowledge to resolve ambiguity in translat….
0
12
0
RT @kayo_yin: 🚨New dataset + challenge #EMNLP2024🚨. We release ASL STEM Wiki: the first signing dataset of STEM articles!. 📰 254 Wikipedia….
0
21
0
RT @ZhongRuiqi: Given the rapid progress of LLMs, I feel compelled to present this topic (even if it's not the main focus of my Ph.D. work)….
0
18
0
RT @ZhongRuiqi: Graphical models struggle to explain patterns in text & images 😭 . LLM can do this but hallucinates. 👿 . It’s time to combi….
0
31
0
RT @ZhongRuiqi: A central concern in alignment is that AI systems will "deceive" humans by doing what looks correct to humans but is actu….
0
13
0
RT @ZhongRuiqi: large mental model update after working on this project. 1. Even when LLM does not know what's correct, it can still learn….
0
12
0
RT @sea_snell: On difficult problems, humans can think longer to improve their decisions. Can we instill a similar capability into LLMs? An….
0
93
0
RT @NickATomlin: New preprint! 📰 Can LMs be improved with AlphaGo-style self-play? The classic answer is that self-play only works in certa….
0
31
0
RT @kayo_yin: Spoken languages exhibit communicative efficiency by minimizing speaker+listener effort. What about signed languages?. Ameri….
0
19
0
RT @YizhouChi: 📝Presenting ThoughtSculpt - a general reasoning & search approach for tasks with decomposable outputs. Leveraging Monte Car….
0
3
0