Alex Warstadt (@a_stadt) header
Alex Warstadt (@a_stadt) profile picture

Alex Warstadt

@a_stadt

Asst Prof. @ UCSD | PI of LeM🍋N Lab | Former Postdoc at ETH Zürich, PhD @ NYU | computational linguistics, NLProc, CogSci, pragmatics | he/him 🏳️‍🌈

alexwarstadt.github.io
Joined September 2016
  • Tweets485
  • Following445
  • Followers1.8K
52Media
Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)Photo by Alex Warstadt (@a_stadt)
I'm excited to announce my new lab: UCSD's Learning Meaning and Natural Language Lab. a.k.a. LeM🍋N Lab! And 📢WE ARE RECRUITING📢 PhD students to join us in sunny San Diego in either Linguistics OR Data Science. Apply by Dec 4: connect.grad.ucsd.edu/apply/ More about the lab👇
Image from Alex Warstadt (@a_stadt)
11
76
2
439
39,298
“We’re friends” “We’re just friends” One tiny word can change how a conversation continues. LLMs pick up on this 👀 We show this through human-LLM comparisons, generation experiments, and mech interp methods. 1/n
Image from Jiahui Karen Chen (@jiahui_k_chen)
Image from Jiahui Karen Chen (@jiahui_k_chen)
1
12
2
40
3,715
🐝New preprint🐝 If you want open source speech technology that's actually optimized for your target language, BuzzASR might be your best option! All models on Huggingface 🤗 Congrats to @realshivamsingh on an amazing first paper!! Appearing in EMNLP Findings.
Shivam Singh (@realshivamsingh) profile pictureShivam Singh@realshivamsinghSep 14
1/ Every language is unique, but the big AI companies release a single model to cover dozens of languages at once. BuzzASR 🐝 takes a different approach: We release a swarm of 102 monolingual speech recognition models, beating Whisper on 77 languages and achieving SOTA on 27.
Image from Shivam Singh (@realshivamsingh)
1
2
21
1,763
Alex Warstadt retweeted
Shivam Singh (@realshivamsingh) profile picture
Shivam Singh@realshivamsinghSep 14
1/ Every language is unique, but the big AI companies release a single model to cover dozens of languages at once. BuzzASR 🐝 takes a different approach: We release a swarm of 102 monolingual speech recognition models, beating Whisper on 77 languages and achieving SOTA on 27.
Image from Shivam Singh (@realshivamsingh)
3
8
6
26
10,237
What can LLMs tell us about the nature of spoken communication? 🗣️🤖 From an info-theory perspective, speech has two main channels: words (text) and melody of speech (prosody). We propose a new method using spoken LLMs to quantify how these channels conveys meaning (1/n)
Title of the paper, "What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels", authors, and the venn diagram depicting the informational relationship between the linguistic channels (prosody P, text T, Audio A) and meaningful feature Y.

ALT Title of the paper, "What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels", authors, and the venn diagram depicting the informational relationship between the linguistic channels (prosody P, text T, Audio A) and meaningful feature Y.

1
12
34
3,273
Alex Warstadt retweeted
Jaap Jumelet (@JumeletJ) profile picture
Jaap Jumelet@JumeletJ15 Oct 2025
🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data! LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data We extend this effort to 45 new languages!
Image from Jaap Jumelet (@JumeletJ)
1
19
4
42
4,563
So excited this work was recognized! We've only scratched the surface of prosodic typology, and I'm even more excited to probe deeper 🔬
Ethan Gotlieb Wilcox (@weGotlieb) profile pictureEthan Gotlieb Wilcox@weGotlieb30 Jul 2025
Honored to have received a Senior Area Chair award at #ACL2025 for our Prosodic Typology paper. Huge shout out to the whole team: @CuiDing_CL, @tpimentelms, @a_stadt, @tamaregev!
12
1,252
Honored to have received a Senior Area Chair award at #ACL2025 for our Prosodic Typology paper. Huge shout out to the whole team: @CuiDing_CL, @tpimentelms, @a_stadt, @tamaregev!
ACL 2027 (@aclmeeting) profile pictureACL 2027@aclmeeting30 Jul 2025
Replying to @aclmeeting
Image from ACL 2027 (@aclmeeting)
4
4
1
56
6,276
So excited about this line of work 👨‍🔬 We use LLMs as a tool 🔧 to better understand linguistic typology: Their ability to learn complex probability distributions 📊 gives quantitative insights into the different strategies languages use to transmit information through prosody 🎶
Ethan Gotlieb Wilcox (@weGotlieb) profile pictureEthan Gotlieb Wilcox@weGotlieb13 May 2025
⭐🗣️New preprint out: 🗣️⭐ “Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent” with @CuiDing_CL, Giovanni Acampa, @tpimentelms, @a_stadt, @tamaregev: arxiv.org/pdf/2505.07659
Image from Ethan Gotlieb Wilcox (@weGotlieb)
3
14
1,659
📣Paper Update 📣It’s bigger! It’s better! Even if the language models aren’t. 🤖New version of “Bigger is not always Better: The importance of human-scale language modeling for psycholinguistics” osf.io/preprints/psyarxiv/rf…
Bigger is not always better: The importance of human-scale language modeling for psycholinguistics

Bigger is not always better: The importance of human-scale language modeling for psycholinguistics

Neural network language models can learn a surprising amount about language by predicting upcoming words in a corpus. Recent language technologies work has demonstrated that large performance...

osf.io
1
5
2
19
5,719
Position opening: #CompLing, #NLP, #CogSci Junior Group Leader / PostDoc (4y, German E14 salary scale) @uni_tue - no teaching obligations - PhD co-supervision - dynamic interdisciplinary team in one of Germany’s top research universities tinyurl.com/jhxb4wu2
16
2
25
5,591
Happy to share that our scientific inquiry paper on training language models with RL **from scratch** has been accepted to #NAACL2025! Many thanks to my collaborator @zekunwang28 💪
Martin Ziqiao Ma (@ziqiao_ma) profile pictureMartin Ziqiao Ma
@ziqiao_ma24 May 2024
Happy to share some “slow research” - it's been 15 months and it's now (finally) on arXiv! Our language development is different from LLMs. We're asking: How do you interactively babysit a language model from scratch, and would it help?🤔 🔗 arxiv.org/abs/2405.13828 @Michigan_AI
Image from Martin Ziqiao Ma (@ziqiao_ma)
4
9
43
4,293
This week I came back to San Diego and successfully defended my dissertation, “A Linguistic Approach to Crosslingual and Multilingual NLP”!
Image from Catherine Arnett @ EMNLP 🇭🇺 (@linguist_cat)
Image from Catherine Arnett @ EMNLP 🇭🇺 (@linguist_cat)
8
5
60
2,368
📣 We are happy to share that CMCL 2025 will be co-located with NAACL in New Mexico! 👉The call for papers is out cmclorg.github.io/CfP SAVE THE DATES, and submit your work! ‼️ Paper submission deadline: Feb 16, 2025 🗓 May 3 or 4, 2025: Workshop (TBA) @naacl @naaclmeeting

Call for Papers

The 2025 Cognitive Modeling and Computational Linguistics workshop.

cmclorg.github.io
1
5
3
21
9,145
Alex Warstadt retweeted
Kevin Du (@kevdududu) profile picture
Kevin Du@kevdududu21 Nov 2024
Very glad and grateful to share this fun work, especially because of the opportunity to work with this immensely talented team--@jkminder, @niklas_stoehr, @giomonea, @wendlerch, @cervisiarius, & Ryan Cotterell 🥳. Check it out!
Julian Minder (@jkminder) profile pictureJulian Minder@jkminder13 Nov 2024
Can we understand and control how language models balance context and prior knowledge? Our latest paper shows it’s all about a 1D knob! 🎛️ arxiv.org/abs/2411.07404 Co-led with @kevdududu, as well as @niklas_stoehr, @giomonea, @wendlerch, @cervisiarius & Ryan Cotterell.
4
13
2,622
I'm in need of NINE emergency reviews for ACL ARR. Over 1/3 of my reviewers are nonresponsive, I think that's a personal record 🙃 Please let me know if you can take on some of these!!
7
4
34
11,450
Thanks everyone for the offers. All papers have emergency reviewers now. So grateful to so many people stepping up!
2
707
If you are interested in topics at the intersection of NLP, Cognitive Science, and Linguistics, please consider applying to the Georgetown PhD program. It's fully funded, and we have a lively 💃🪩🕺 interdisciplinary community on campus!
Nathan Schneider (@complingy) profile pictureNathan Schneider@complingy7 Nov 2024
Replying to @complingy
Also note that Georgetown is accepting applications for M.S. & Ph.D. in Computational Linguistics (core faculty: Ethan Wilcox @weGotlieb, Amir Zeldes, and myself). Announcement: list.elra.info/mailman3/hype…
23
1
92
12,258
LeM🍋N Lab is an essentially **interdisciplinary** group. We use advances in NLP to investigate how humans learn language and why language is the way it is. And we use insights from Linguistics and CogSci to evaluate and interpret LMs and advance data-efficient pretraining.
1
12
1,451
Specific topics include: -LMs as models of human learners -Efficient LM pretraining -Bayesian & experimental pragmatics -Information-theoretic linguistics -Prosody and speech processing -Multimodal pretraining -Grammatical evaluation For prospective PhDs: alexwarstadt.github.io/news/…
11
1,296
Load more