Lightnews — Scholar-powered news

Reposted by Tal Linzen

NYU Center for Data Science @nyudatascience.bsky.social · 28d

Linguistics PhD student @jacksonpetty.org finds LLMs "quiet-quit" when instructions get long, switching from reasoning to guesswork.

With CDS' @tallinzen.bsky.social, @shauli.bsky.social, @lambdaviking.bsky.social, @michahu.bsky.social, and Wentao Wang.

nyudatascience.medium.com/llms-switch-...

LLMs Switch to Guesswork Once Instructions Get Long

LLMs abandon reasoning for guesswork when instructions get long, new work from Linguistics PhD student Jackson Petty & CDS shows.

nyudatascience.medium.com

2 7

Reposted by Tal Linzen

Dr. Lucky Tran @luckytran.com · Jul 11

DO NOT GIVE UP!

Our advocacy is working.

A key Senate committee has indicated that it will reject Trump’s proposed cuts to science agencies including NASA and the NSF.

Keep speaking up and calling your electeds 🗣️🗣️🗣️

Nature: US senators poised to reject Trump’s proposed massive science cuts

Committee gives first hint that policymakers might preserve, rather than slash, funding for US National Science Foundation and other agencies.

8 450 1.3K

Tal Linzen @tallinzen.bsky.social · Jul 11

Maybe five years with a no-cost extension!

3

Tal Linzen @tallinzen.bsky.social · Jul 11

Congratulations to @linguistbrian.bsky.social for receiving this grant to study how to constrain language models to read complex sentences more like humans, and congratulations to me for getting to collaborate with him for another four years! www.umass.edu/humanities-a...

Brian Dillon Receives NSF Grant to Explore AI and Human Language Processing : College of Humanities & Fine Arts : UMass Amherst

Linguist Brian Dillon receives NSF grant to investigate how AI and humans differ in interpreting meaning during language comprehension.

www.umass.edu

1 1 17

Tal Linzen @tallinzen.bsky.social · Jul 2

Thanks Andrea!

Tal Linzen @tallinzen.bsky.social · Jul 2

If we have a lot of shared followers, perhaps you could comment on the pinned tweet on my account and provide context?! Thank you!

1 1

Tal Linzen @tallinzen.bsky.social · Jul 2

My Twitter account has been hacked :( Please don't click on any links "I" posted on that account recently!

1 1 2

Tal Linzen @tallinzen.bsky.social · Jun 21

I'll be accepting applications for a while, and will also consider people with a late start date. Feel free to email if you have questions. No need for a formal cover letter.

Tal Linzen @tallinzen.bsky.social · Jun 21

The goal is to model some cool behavioral and neural data from humans (some to be collected) but we expect to do a lot of fundamental modeling and interpretability work. You don't need to have existing experience in cognitive science but you should be interested in learning more about it.

1 2

Tal Linzen @tallinzen.bsky.social · Jun 21

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...

NYU LLM + cognitive science post-doc interest form

Tal Linzen's group at NYU is hiring a post-doc! We're interested in creating language models that process language more like humans than mainstream LLMs do, through architectural modifications and int...

docs.google.com

2 22 41

Tal Linzen @tallinzen.bsky.social · Jun 20

דווקא בביקורת הדרכונים בצד הישראלי של המעבר לא ביקשו הוכחה שיש לי גם דרכון זר, נתנו לי לצאת מהארץ בלי בעייה. מסתבר שיש סיכון בטחוני ביציאה מהארץ של אזרחים ישראלים רק בדרך האוויר, לא בדרך היבשה

3

Reposted by Tal Linzen

Jackson Petty @jacksonpetty.org · Jun 9

How well can LLMs understand tasks with complex sets of instructions? We investigate through the lens of RELIC: REcognizing (formal) Languages In-Context, finding a significant overhang between what LLMs are able to do theoretically and how well they put this into practice.

1 2 5

Reposted by Tal Linzen

Arianna Bisazza @arianna-bis.bsky.social · May 30

Following the success story of BabyBERTa, I & many other NLPers have turned to language acquisition for inspiration. In this new paper we show that using Child-Directed Language as training data is unfortunately *not* beneficial for syntax learning, at least not in the traditional LM training regime

Francesca Padovani @frap98.bsky.social · May 30

“Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models”

I’m happy to share that the preprint of my first PhD project is now online!

🎊 Paper: arxiv.org/abs/2505.23689

Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models

Seminal work by Huebner et al. (2021) showed that language models (LMs) trained on English Child-Directed Language (CDL) can reach similar syntactic abilities as LMs trained on much larger amounts of ...

arxiv.org

1 6 24

Tal Linzen @tallinzen.bsky.social · May 24

Depends on what you mean by US academics, I guess. A lot of people are here for a temporary position, don't have strong ties to the country, and were mentally prepared to move elsewhere anyway. Those people are much more likely to leave than before.

1 7

Tal Linzen @tallinzen.bsky.social · May 23

I'll have a bit of time to chat with folks in Berlin and/or Copenhagen about AI, LLMs, cognitive science, how good your bike infrastructure is, etc, let me know!

1

Tal Linzen @tallinzen.bsky.social · May 23

And this one on language models with cognitively plausible memory in Potsdam on Tuesday (as part of this in-person-only sentence processing workshop vasishth.github.io/sentproc-wor...):

1 5

Tal Linzen @tallinzen.bsky.social · May 23

Cross-posting the abstracts for two talks I'm giving next week! This one on formal languages for LLM pretraining and evaluation, at Apple ML Research in Copenhagen on Wednesday

1 2 9

Tal Linzen @tallinzen.bsky.social · May 12

Updated version of our position piece on how language models can help us understand how people learn and process language, on why it's crucial to train models on cognitive plausible datasets, and on the BabyLM project that addresses this issue.

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 12

📣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/ps...

OSF

osf.io

1 11

Tal Linzen @tallinzen.bsky.social · May 1

out of date, should be $300 billion now!

9

Tal Linzen @tallinzen.bsky.social · Mar 27

thanks! I'll start with the frens and nice people and work my way up from there!

2

Reposted by Tal Linzen

Dario Paape @dariopaape.bsky.social · Mar 14

At #HSP2025, I'll present work with @tallinzen.bsky.social and @shravanvasishth.bsky.social on modeling garden-pathing in a huge benchmark dataset: hsp2025.github.io/abstracts/29.... Statistically decomposing the effect into subprocesses greatly improves predictive fit over just comparing means!

hsp2025.github.io

2 11

Tal Linzen @tallinzen.bsky.social · Mar 27

Going to give this website another shot! What are good lists of linguistics, psycholinguistics, NLP and AI accounts?

4 15

Tal Linzen @tallinzen.bsky.social · Nov 19

Thanks Ted for mentioning me in the same tweet as Chris! This website really is better than the other one!

Ted Underwood @tedunderwood.com · Nov 12

Another good sign for this platform is that people like @tallinzen.bsky.social and @chrmanning.bsky.social are dipping their toes in it (even if no pfps yet). Give them a follow if you know who they are.

4

Tal Linzen @tallinzen.bsky.social · Nov 19

Very little happening on here but silence is certainly better than all of the boardroom drama takes on the other website. Four different people I follow just came up with the same unfunny joke about the most recent development in the drama, apparently independently?

10

Reposted by Tal Linzen

Jackson Petty @jacksonpetty.org · Nov 10

Do deep transformer LMs generalize better? In a new preprint we (Sjoerd van Steenkiste, Ishita Dasgupta, Fei Sha, Dan Garrette, & @tallinzen.bsky.social) control for parameter count to show how depth helps models on compositional generalization tasks, but diminishingly so 🧵

jacksonpetty.org/depth

The Impact of Depth and Width on Transformer Language Model Generalization

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Fo...

jacksonpetty.org

1 5 10