Love to start the day by mistakenly stumbling onto hate speech against south-asians ty internet

Accepted at #NeurIPS2025! So proud of Yulu and Dheeraj for leading this! Be on the lookout for more "nuanced yes/no" work from them in the future 👀

Abstract deadline changed to *December 1, 2025*

📣@futrell.bsky.social and I have a BBS target article with an optimistic take on LLMs + linguistics. Commentary proposals (just need a few hundred words) are OPEN until Oct 8. If we are too optimistic for you (or not optimistic enough!) or you have anything to say: www.cambridge.org/core/journal...

Happy and proud to see @rjantonello.bsky.social’s work awarded by SNL!

Exhibit N on how synthetic text/AI detectors just don't work reliably. Generating some (long) sentences from GPT4.1 and GPT5 with the same prompt, the top open-source model on the RAID benchmark classifies most GPT4.1 outputs as synthetic and most GPT5 as not synthetic.

Super happy with Cogsci program assistant Chris Kent's work for our college Instagram feed. Glad I could get our Loki featured to advertise my class.

Excited to speak alongside such an illustrious set of speakers!

Lovely write up by @ksetiya.bsky.social on @rkubala.bsky.social’s piece on the art of crosswords! Come for Robbie, stay for Sondheim crossword quotes. ksetiya.substack.com/p/compositio...

🤖 🧠 NEW PAPER ON COGSCI & AI 🧠 🤖 Recent neural networks capture properties long thought to require symbols: compositionality, productivity, rapid learning So what role should symbols play in theories of the mind? For our answer...read on! Paper: arxiv.org/abs/2508.05776 1/n

Are similar representations in neural nets evidence of shared computation? In new theory work w/ Lukas Braun (lukasbraun.com) & @saxelab.bsky.social, we prove that representational comparisons are ill-posed in general, unless networks are efficient. @icmlconf.bsky.social @cogcompneuro.bsky.social

The Echoes in AI paper showed quite the opposite with also a story continuation setup. Additionally, we present evidence that both *syntactic* and *discourse* diversity measures show strong homogenization that lexical and cosine used in this paper do not capture.

ACL shortpaper appreciation thread because shortpapers are the best papers. What's the best <=5 pager? I'm nominating an oldie but a goodie

Why does neurips hide the reviewers' updated scores (or lack thereof)? "this is to maximize misery for everyone" - aptly described by @najoung.bsky.social

In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:

can someone pls remove the "em-dashes" feature from all LLMs??? I refuse to give up on 'em

Doug’s papers on concepts and categories (along with Smith, Murphy) had a heavy influence on me during PhD! So happy his work was recognized!!! And such a powerful speech too 🙏

Happening now at the SIGTYP poster session! Come talk to Leonie and me about MultiBLiMP!

Puh-lease!

How do future plans affect word form & word choice in online production? With @futrell.bsky.social in #Cogsci25, we examine the backward predictability effect & introduce a principled variant of backward planning that preserves info proc dependencies b/w words in the past and future context (1/9)

going to a conference without carrying a poster tube or worrying about slides, and on top of that posting to RECRUIT students as opposed to finding new opportunities -- what a strange, funny feeling!

Looking forward to attending #cogsci2025 (Jul 29 - Aug 3)! I’m especially excited to meet students who will be applying to PhD programs in Computational Ling/CogSci in the coming cycle. Please reach out if you want to meet up and chat! Email is the best way, but DM also works if you must! quick🧵:

🚨📊ɴᴇᴡ ᴘᴀᴘᴇʀ!! When we learn a new skill—like tying shoelaces or making pasta—we often start with a series of deliberate steps. But eventually, those steps blend into a smooth, single unit: an action chunk. But why and when do we chunk? 👇 📰https://authors.elsevier.com/a/1lMMD2Hx2-9B8

👾 Full-time research assistant position (1 year) with @sebschu.bsky.social and me! 👾 We're looking for someone to join the research agent evaluation team, starting Fall 2025. Application link to be available soon, but feel free to send us your CV and/or come talk to us at #ACL2025. 🧵

Next week I’ll be in Vienna for my first *ACL conference! 🇦🇹✨ I will present our new BLiMP-NL dataset for evaluating language models on Dutch syntactic minimal pairs and human acceptability judgments ⬇️ 🗓️ Tuesday, July 29th, 16:00-17:30, Hall X4 / X5 (Austria Center Vienna)

“Seeing” robins and sparrows does not necessarily make them internally birdier to LMs! Check out new work by @yuluqin.bsky.social and Dheeraj showing that while the above is true Vision training does improve the deployment of this knowledge!

I am especially excited about our cute little case study showcasing that within MLM embs, different dative-constructions with the same lexical items construe different levels of animacy vs. place-hood information onto the recipient (DO: animate; PO: place/location)

I will unfortunately have to skip SCiL this year, but I am thrilled to share that Jwalanthi will be presenting this work by her, @rjha.bsky.social, me, and @kmahowald.bsky.social on a tool that allows you to project contextualized embeddings from LMs to interpretable semantic spaces!

My grandmother passed away a few moments ago. She was suffering from a mental illness (a rare form of dementia). It’s likely that my love for language comes from her - she was a school teacher and taught Sanskrit, Odia, and English. I hope she is at peace now.

Binz et al. (in press, Nature) developed an LLM called Centaur that better predicts human responses in 159 of 160 behavioural experiments compared to existing cognitive models. See: arxiv.org/abs/2410.20268

colmed!

🎤 "Your #CogSci presentation was quite good this year." How flattered or offended will you be? The answer may depend on whether you speak British or American English 🇺🇸🇬🇧. Our new #CogSci2025 paper reveals systematic differences in how different cultures interpret the same words.

Two nice papers now added to my primer of what to read about theory in cognitive science ... docs.google.com/document/d/1... 1/

👀 amazing name amazing execution! Worth reading!!

Experimentology is out today!!! A group of us wrote a free online textbook for experimental methods, available at experimentology.io - the idea was to integrate open science into all aspects of the experimental workflow from planning to design, analysis, and writing.

I'm excited about this TICS Opinion with @yngwienielsen.bsky.social, challenging the view that structural priming—the tendency to reuse a recent syntactic structure—provides evidence for the psychological reality of grammar-based constituent structure. authors.elsevier.com/a/1lIFK4sIRv... 🧵1/4

🚨 New preprint! 🚨 Phase transitions! We love to see them during LM training. Syntactic attention structure, induction heads, grokking; they seem to suggest the model has learned a discrete, interpretable concept. Unfortunately, they’re pretty rare—or are they?

What makes humans similar or different to AI? In a paper out in @natmachintell.nature.com led by @florianmahner.bsky.social & @lukasmut.bsky.social, w/ Umut Güclü, we took a deep look at the factors underlying their representational alignment, with surprising results. www.nature.com/articles/s42...

I'm hiring at least one post-doc! We're interested in creating language models that process language more like humans than mainstream LLMs do, through architectural modifications and interpretability-style steering. Express interest here: docs.google.com/forms/d/e/1F...

Is anyone talking about the big design flaws in this study, e.g. 1) small N, btwn subject design, 2) v. heterogeneous sample, 3) writing prompt confounded with condition (really!), 4) vast number of measures with no preregistration? I can't believe this is getting so much press...

Hey it’s me soliciting volunteers for emergency reviewing (ARR) again! This time on Chain of Thought reasoning - pls dm me if you’re available!

Are there any good LLMs pretrained only on pre-2010 or pre-2000 text?

ACL paper alert! What structure is lost when using linearizing interp methods like Shapley? We show the nonlinear interactions between features reflect structures described by the sciences of syntax, semantics, and phonology.

I'm joining Princeton University as an Associate Professor of Computer Science and Psychology this fall! Princeton is ambitiously investing in AI and Natural & Artificial Minds, and I'm excited for my lab to contribute. Recruiting postdocs and Ph.D. students in CS and Psychology — join us!

Looking for someone to review a paper on counterfactual reasoning for this ARR cycle (mildly urgent)!

When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs: 🧵1/9

Very nice of Alcaraz and Sinner to put on such a spectacle before the world ends!

Looking for studies that compare similarity judgments/conceptual knowledge of people with / without forms of color-blindness?

Language is often strategic, but LLMs tend to play nice. How strategic are they really? Probing into that is key for future safety alignment. 👉Introducing CoBRA🐍, a framework that assesses strategic language. Work with my amazing advisors @jessyjli.bsky.social and @David I. Beaver!

I’m thrilled to share that I will be joining Johns Hopkins University’s Department of Computer Science (@jhucompsci.bsky.social, @hopkinsdsai.bsky.social) as an Assistant Professor this fall.