iiinova — where your digital self keeps evolving

Sasha Boguraev @sashaboguraev.bsky.social · 18h

I’ll be at COLM this week, presenting this work on Wednesday afternoon! Excited to talk about LM [interpretability, cognition, and meta-cognition] and the interplay between all of them. Reach out if you’d like to chat!

031

Sasha Boguraev @sashaboguraev.bsky.social · 04/09/2026

Linguistic theory has long recognized cross-linguistic syntactic regularities, leading to claims that these similar structures are processed by similar mechanisms. We test this hypothesis in modern multilingual LMs. New work with Toshiki Nakai, @kmahowald.bsky.social , and @telufinwe.bsky.social!🧵👇

141

Sasha Boguraev @sashaboguraev.bsky.social · 21/07/2026

I’ll be in Rio this week to present this at CogSci! Excited to talk about what the study of LM interp (and LMs more broadly!) can contribute to studies of Cognitive Science and Linguistic Theory. Reach out if you’d like to chat!

073

Reposted by Sasha Boguraev

Kyle Mahowald @kmahowald.bsky.social · 18/07/2026

(2) Come see @sashaboguraev.bsky.social (who will be in rio as well) on Saturday presenting our artificial neural take (also with @qyao.bsky.social) on a disjunction puzzle re the non-redundancy of "She will go to France or Spain, or perhaps to Germany or France." arxiv.org/abs/2602.23547

arxiv.org

France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions

Sentences like "She will go to France or Spain, or perhaps to Germany or France." appear formally redundant, yet become acceptable in contexts such as "Mary will go to a philosophy program in France o...

141

Reposted by Sasha Boguraev

Kyle Mahowald @kmahowald.bsky.social · 02/07/2026

The full BBS treatment from me and @futrell.bsky.social on "How linguistics learned to stop worrying and love the LMs" is now out, with all the commentaries and our response. If you "Save PDF", it will give you the whole target article + commentary + response pdf: www.cambridge.org/core/journal...

cambridge.org

How linguistics learned to stop worrying and love the language models | Behavioral and Brain Sciences | Cambridge Core

How linguistics learned to stop worrying and love the language models - Volume 49

2359

Reposted by Sasha Boguraev

Kanishka Misra @kanishka.bsky.social · 11/05/2026

New opinion piece on the interface between research on concepts and categories in minds vs. in neural network LMs! I take the position that there is much to be learned from this interface (e.g., learning about concepts from language alone) and outline some directions for future.

Title page of "Semantic Cognition for and from Language Models" followed by a figure showing tests that target conceptual structure and content vs. those that target function.

25712

Sasha Boguraev @sashaboguraev.bsky.social · 08/05/2026

"She'll go to France or Spain or Germany or France" sounds redundant—unless licensed with context like "She will go to an art program in France or Spain or a math program in Germany or France" In new work w/ @qyao.bsky.social and @kmahowald.bsky.social: an LM-based 'Neural Semantics' account 🧵👇

1153

Reposted by Sasha Boguraev

Kyle Mahowald @kmahowald.bsky.social · 17/04/2026

Richard @futrell.bsky.social and I have posted our response to the commentaries on our BBS target article "How Linguistics Learned to Stop Worrying and Love the Language Models." The response is: "You Can't Fight in Here! This is BBS!" arxiv.org/abs/2604.09501

arxiv.org

You Can't Fight in Here! This is BBS!

Norm, the formal theoretical linguist, and Claudette, the computational language scientist, have a lovely time discussing whether modern language models can inform important questions in the language ...

13513

Sasha Boguraev @sashaboguraev.bsky.social · 16/04/2026

Perhaps more ink has been spilled on the topic of Island Constraints than any other such phenomenon in theoretical linguistics. In new work with @kmahowald, we study how LMs process such phenomenon, using techniques from mechanistic interpretability to guide our exploration. 🧵👇

2184

Sasha Boguraev @sashaboguraev.bsky.social · 16/04/2026

I seem to remember a paper from a few months ago about how even high-precision SAE feature labels have low-recall, but I can't for the life of me find it. Can someone point me in the right direction or did I hallucinate this?

000

Sasha Boguraev @sashaboguraev.bsky.social · 13/12/2025

If you or a love one suffers from `riding a motorcycle the wrong direction in the NYC bike lanes' syndrome you may be entitled to compensation in the form of me yelling at you on my run.

010

Sasha Boguraev @sashaboguraev.bsky.social · 21/11/2025

We are accepting submissions for the 25th edition of the Texas Linguistics Society (TLS), a UT Austin grad-student ran Linguistics conference! The conference will run from February 20 - 21, 2026 in Austin. Abstract Deadline: December 17 Notification: January 15

132

Reposted by Sasha Boguraev

Kyle Mahowald @kmahowald.bsky.social · 07/11/2025

Delighted Sasha's (first year PhD!) work using mech interp to study complex syntax constructions won an Outstanding Paper Award at EMNLP! Also delighted the ACL community continues to recognize unabashedly linguistic topics like filler-gaps... and the huge potential for LMs to inform such topics!

aclanthology.org

1338

Sasha Boguraev @sashaboguraev.bsky.social · 11/10/2025

Curious as to if people think if (when?) ‘superhuman AI’ arrives, will the building blocks of its performance be human recognizable concepts which have been applied and combined in new and novel ways to achieve ‘superhuman’ performance? Or will it be completely uninterpretable?

342

Reposted by Sasha Boguraev

Kyle Mahowald @kmahowald.bsky.social · 07/10/2025

UT Austin Linguistics is hiring in computational linguistics! Asst or Assoc. We have a thriving group sites.utexas.edu/compling/ and a long proud history in the space. (For instance, fun fact, Jeff Elman was a UT Austin Linguistics Ph.D.) faculty.utexas.edu/career/170793 🤘

sites.utexas.edu

UT Austin Computational Linguistics Research Group – Humans processing computers processing humans processing language

14126

Sasha Boguraev @sashaboguraev.bsky.social · 06/10/2025

I will be giving a short talk on this work at the COLM Interplay workshop on Friday (also to appear at EMNLP)! Will be in Montreal all week and excited to chat about LM interpretability + its interaction with human cognition and ling theory.

084

Reposted by Sasha Boguraev

Kanishka Misra @kanishka.bsky.social · 30/09/2025

The compling group at UT Austin (sites.utexas.edu/compling/) is looking for PhD students! Come join me, @kmahowald.bsky.social, and @jessyjli.bsky.social as we tackle interesting research questions at the intersection of ling, cogsci, and ai! Some topics I am particularly interested in:

Picture of the UT Tower with "UT Austin Computational Linguistics" written in bigger font, and "Humans processing computers processing human processing language" in smaller font

3189

Sasha Boguraev @sashaboguraev.bsky.social · 15/08/2025

Breaking my years-long vow to never fly American Airlines just to be met with a 6 hr delay and 5am arrival back home 🫠

120

Sasha Boguraev @sashaboguraev.bsky.social · 27/05/2025

A key hypothesis in the history of linguistics is that different constructions share underlying structure. We take advantage of recent advances in mechanistic interpretability to test this hypothesis in Language Models. New work with @kmahowald.bsky.social and @cgpotts.bsky.social! 🧵👇!

1305

Reposted by Sasha Boguraev

Qing Yao @qyao.bsky.social · 31/03/2025

LMs learn argument-based preferences for dative constructions (preferring recipient first when it’s shorter), consistent with humans. Is this from memorizing preferences in training? New paper w/ @kanishka.bsky.social , @weissweiler.bsky.social , @kmahowald.bsky.social arxiv.org/abs/2503.20850

examples from direct and prepositional object datives with short-first and long-first word orders:
DO (long first): She gave the boy who signed up for class and was excited it.
PO (short first): She gave it to the boy who signed up for class and was excited.
DO (short first): She gave him the book that everyone was excited to read.
PO (long-first): She gave the book that everyone was excited to read to him.

1177

Reposted by Sasha Boguraev

Siyuan Song @siyuansong.bsky.social · 12/03/2025

New preprint w/ @jennhu.bsky.social @kmahowald.bsky.social : Can LLMs introspect about their knowledge of language? Across models and domains, we did not find evidence that LLMs have privileged access to their own predictions. 🧵(1/8)

26116

Sasha Boguraev @sashaboguraev.bsky.social · 15/12/2024

Notoriously finicky BC weather celebrating the last day of #NeurIPS2024 with a rainbow across the harbor

050

Sasha Boguraev @sashaboguraev.bsky.social · 14/12/2024

I'll be presenting a position piece (arxiv.org/abs/2409.17005) on what cognitive science and linguistics can bring to the Math + AI field tomorrow from 11:00 -12:30 and 4:00 - 5:00 at the (aptly named) #NeurIPS2024 MathAI Workshop in West Meeting Room 118-120. Come say hi and hear about my work!

arxiv.org

Models Can and Should Embrace the Communicative Nature of Human-Generated Math

Math is constructed by people for people: just as natural language corpora reflect not just propositions but the communicative goals of language users, the math data that models are trained on reflect...

0175

Reposted by Sasha Boguraev

Kyle Mahowald @kmahowald.bsky.social · 13/12/2024

In Vancouver for #NeurIPS2024 workshops! At Math-AI tomorrow @sashaboguraev.bsky.social is presenting our experiment-infused position piece on the communicative nature of math and why that matters for AI arxiv.org/pdf/2409.17005. Say hi! Will be better than the Panthers 4-0 loss to the Canucks.

arxiv.org

081

Sasha Boguraev @sashaboguraev.bsky.social · 10/12/2024

I’m at NeurIPS all week! On 12/14 I’ll present on viewing math as a communicative activity at the MathAI workshop. Meanwhile, I’d love to chat about this work or more broadly about communicative framing in NLP, including emergent communication paradigms, language games and more. Please reach out!

020