Sathvik @sathvikn4

computational psycholinguistics @ umd, nsf grfp fellow | he/him | fmr: cognitive & computer science @ uc berkeley | also on bluesky (sathvik@) sathvikn.github.io DC Joined November 2017

Tweets

2K
Followers

838
Following

1K
Likes

22K

Huy Nghiem @hnghiem_ai

7 days ago

How do AI models reason in high-stakes decisions like college admissions? We that Large Language Models can display equity-oriented patterns—but also volatile reasoning that underscores the need for transparency, fairness, and accountability ? (1/n) Link: arxiv.org/abs/2509.16400

Huy Nghiem @hnghiem_ai

a month ago

0 0 11 1K 1

Download Image

6 3 5 841 0

Shangbin Feng @shangbinfeng

2 weeks ago

Seems to me the "findings of *ACL" decision is really wise and visionary (5 years ago), compared to the "had to reject because of venue limit" thing

2 9 89 17K 2

William Matchin @wmatchin

2 weeks ago

@davidpoeppel receiving the well-deserved @SNLmtg Distinguished Career Award David has had a lasting and deep impact on the field and on his many successful trainees. David is also known for his enjoinders to engage positively with the world. #SNL2025

1 4 22 2K 0

Download Image

Shravan Vasishth @ShravanVasishth

2 weeks ago

New preprint investigating whether lossy-context surprisal can account for the locality and expectation effects found in Russian, Hindi, and Persian reading data: osf.io/preprints/psya…

0 3 15 485 2

Xinchi Yu @Xinchi_Yu

3 weeks ago

How I wish I could be at SNL in DC! If you are there, please do check in on my University of Maryland folks (tons of fun stuff happening over there), and have some soft-shell crabs 🦀️on my behalf! xD linguistics.umd.edu/news/maryland-…

0 1 5 322 0

Sebastián Mancha @seb_mancha

3 weeks ago

If anyone is around for SNL down the block from me, I have a sandbox poster Sunday! I present some very preliminary data examining cued sentence recall with MEG. If you care about sentence recall, MEG sentence production, or combining psycholing+memory tasks, stop by poster E19!

0 1 1 220 0

Shota Momma @shota_momma

2 months ago

A paper with Vic Ferreira and Norvin Richards is now out in JML! (1) Speakers syntactically encode zero complementizers as cognitively active mental object. (2) No evidence LLMs capture cross constructional generalizations about zero complementizers. nam10.safelinks.protection.outlook.com/?url=https%3A%…

1 10 30 2K 12

Sathvik @sathvikn4

2 months ago

Friends at Cogsci, I’ll be in SF tomorrow and would love to catch up if you’re there! I should be around from lunch onwards, my DMs/texts/emails are open.

1 0 9 596 0

Neha Srikanth @nehasrikanth

2 months ago

When questions are poorly posed, how do humans vs. models handle them? Our #ACL2025 paper explores this + introduces a framework for detecting and analyzing poorly-posed information-seeking questions! Joint work with @boydgraber & @rachelrudinger! 🔗 aclanthology.org/2025.acl-long.…

6 14 61 4K 12

Download Image

Lindia Tjuatja @lltjuatja

2 months ago

Slept in after last night’s social? You can still catch my poster from 11-12:30 today!

Lindia Tjuatja @lltjuatja

4 months ago

Slept in after last night’s social? You can still catch my poster from 11-12:30 today! https://t.co/rx0U1uMzdn

1 33 155 33K 66

Download Image

0 6 50 15K 8

Download Image

Dallas Card @dallascard

2 months ago

I am delighted to share our new #PNAS paper, with Gaurav Kamath, @mjieyang @sivareddyg and @masonderegger, looking at whether age matters for the adoption of new meanings. That is, as words change meaning, does the rate of adoption vary across generations? pnas.org/doi/10.1073/pn…

1 8 36 3K 4

Download Image

Rupak @rupak_53

2 months ago

Linguistic theory tells us that common ground is essential to conversational success. But to what extent is it essential? Can LLMs detect when humans lose common ground in conversation? Our ACL 2025 (Oral) paper explores these questions on real-world data. #ACL2025NLP #ACL2025

1 7 27 4K 4

Download Image

Kanishka Misra 🌊 @kanishkamisra

2 months ago

I will unfortunately have to skip SCiL this year, but I am thrilled to share that Jwalanthi will be presenting this work by her, @Robro612, me, and @kmahowald on a tool that allows you to project contextualized embeddings from LMs to interpretable semantic spaces!

2 4 32 1K 6

Download Image

Philip Resnik @psresnik

2 months ago

To be presented at ACL 2025: Large Language Models Are Biased Because They Are Large Language Models. Article: doi.org/10.1162/coli_a… Short (8min) video: youtube.com/watch?v=WLSuhe… #ACL2025NLP #NLProc #LLMs

0 16 51 3K 13

Zhu Jian-Qiao @JQ_Zhu

3 months ago

Centaur may have learned a shortcut that explains away psychological tasks. @PsychBoyH Link to preprint: osf.io/preprints/psya…

4 21 109 33K 48

Download Image

Dileep George @dileeplearning

3 months ago

"A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws".

Keyon Vafa @keyonV

3 months ago

"A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws".

212 1K 7K 1.4M 5K

Download Video

10 26 192 19K 71

Harvey Yiyun Fu @harveyiyun

3 months ago

LLMs excel at finding surprising “needles” in very long documents, but can they detect when information is conspicuously missing? 🫥AbsenceBench🫥 shows that even SoTA LLMs struggle on this task, suggesting that LLMs have trouble perceiving “negative space” in documents. paper:…

11 33 159 26K 68

Download Image

Isabel Papadimitriou @isabelpapad

4 months ago

Check out our ACL paper! We use shapley interactions to see which words (and phones) interact non-linearly -- what we lose when we assume linear relationships between features. Chat to Diganta in Vienna!

Naomi Saphra @nsaphra

4 months ago

1 4 42 8K 32

Download Image

0 9 37 3K 6

UMD CLIP Lab @ClipUmd

4 months ago

Researchers @UofMaryland are examining how and why some misleading narratives proliferate via strategic use of certain mainstream news articles. The paper—coauthored by Pranav Goel, @_Jon_Green, @davidlazer & @psresnik—was published @NatureHumBehav. nature.com/articles/s4156…

1 5 7 922 0

Byung-Doh Oh @byungdoh

4 months ago

Is the slowdown in reading at low-frequency words separable from predictability effects? Studies using LM surprisal like doi.org/10.1162/opmi_a… suggest so. Our new JML paper doi.org/10.1016/j.jml.… instead argues it may depend on the LM, which is itself sensitive to frequency.