Profile avatar
kmahowald.bsky.social
UT Austin linguist http://mahowak.github.io/. computational linguistics, cognition, psycholinguistics, NLP, crosswords. occasionally hockey?
55 posts 2,800 followers 502 following
Regular Contributor
Active Commenter
Posts 23 Comments 27

Check out our new work on introspection in LLMs! 🔍 TL;DR we find no evidence that LLMs have privileged access to their own knowledge. Beyond the study of LLM introspection, our findings inform an ongoing debate in linguistics research: prompting (eg grammaticality judgments) =/= prob measurement!

submitted 20 hours ago • 0 comments

If I ask model A “is this sentence grammatical” and it says yes, does that mean model A is more likely to produce that sentence than model B? Check out our new paper on whether models introspect about knowledge of language.

submitted 23 hours ago • 1 comment

I'm excited to announce two papers of ours which will be presented this summer at @naaclmeeting.bsky.social eting.bsky.social and @iclr-conf.bsky.social ! 🧵

submitted 1 day ago • 1 comment

Check it out for cool plots like this about how affinities between words in sentences and how they can show how Green Day isn't like green paint or green tea. And congrats to @coryshain.bsky.social and the CLiMB lab! climblab.org

submitted 1 day ago • 3 comments

I just had a chance to watch this fantastic talk. I really recommend it for anyone interested in how LLMs can help us understand language: www.youtube.com/watch?v=DBor...

submitted 26 days ago • 1 comment

Looking forward to speaking tomorrow (Tues am) in this Simons workshop in Berkeley simons.berkeley.edu/workshops/ll.... Will talk about some empirical work and also share some takes from this recent preprint from me and @futrell.bsky.social arxiv.org/abs/2501.17047

submitted 37 days ago • 0 comments

LMs need linguistics! New paper, with @futrell.bsky.social, on LMs and linguistics that conveys our excitement about what the present moment means for linguistics and what linguistics can do for LMs. Paper: arxiv.org/abs/2501.17047. 🧵below.

submitted 42 days ago • 3 comments

LMs need linguistics! New paper, with @futrell.bsky.social, on LMs and linguistics that conveys our excitement about what the present moment means for linguistics and what linguistics can do for LMs. Paper: arxiv.org/abs/2501.17047. 🧵below.

submitted 42 days ago • 3 comments

This is a beautiful paper! The first third helpfully labels a stream of recent work in philosophy of AI as "propositional interpretability". The idea is to use propositional attitudes like belief, desire, and intention, to help explain AI in a way that we can understand. 1/n

submitted 43 days ago • 2 comments

Quanta write-up of our Mission: Impossible Language Models work, led by @juliekallini.bsky.social. As the photos suggest, Richard, @isabelpapad.bsky.social, and I do all our work sitting together around a single laptop and pointing at the screen.

submitted 58 days ago • 0 comments

If this is anything like the live version at the LSA (and it seems to be!), it's worth watching for an inspiring vision for how linguistics and LLMs can fit together...and, as this slide near the end shows, how linguistic phenomena can be described neurally, artificial-neurally, or symbolically.

submitted 58 days ago • 0 comments

I like the NLP reference in "Walking in a Winter Wonderland", where they say "In the meadow, we can build a snowman / Then pretend that he is parsin' [the] Brown [corpus]"

submitted 78 days ago • 1 comment

LSA president Tony Woodbury on Sapir's idea that each language has its own "genius", and that each language should be described with its own framework, rather than through a general ("theoretical") framework. muse.jhu.edu/article/948426

submitted 81 days ago • 0 comments

I defended my PhD at MIT Brain&Cog last week--so much gratitude to my advisor @evfedorenko.bsky.social, as well as my committee @nancykanwisher.bsky.social, @joshhmcdermott.bsky.social and Yoon Kim. Thank you to all my brilliant collaborators and the MIT community. I have loved this journey so much.

submitted 87 days ago • 6 comments

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.

submitted 89 days ago • 0 comments

Christian Uffmann wins linguist prof of 2024. This video is iconic. Definitely worth watching and I say this as someone who is terminally not interested in watching video content. www.youtube.com/watch?v=pSOl...

submitted 97 days ago • 11 comments

Cool project! And very impressed by the first author’s choice of last name and also university.

submitted 99 days ago • 1 comment

Three ManyBabies projects - big collaborative replications of infancy phenomena - wrapped up this year. The first paper came out this fall. I thought I'd take this chance to comment on what I make of the non-replication result. 🧵 bsky.app/profile/laur...

submitted 99 days ago • 2 comments

submitted 112 days ago • 0 comments

Our new paper “Is Child-Directed Speech Effective Training Data for Language Models?” was just presented at #EMNLP2024! This is work led by Steven Feng, with Noah Goodman. arxiv.org/abs/2408.03617

submitted 112 days ago • 2 comments

💬 Have you or a loved one compared LM probabilities to human linguistic acceptability judgments? You may be overcompensating for the effect of frequency and length! 🌟 In our new paper, we rethink how we should be controlling for these factors 🧵:

submitted 112 days ago • 1 comment

The University of Texas at Austin's Dept. of Linguistics is hiring two tenure-track positions in computational linguistics with a focus on research connecting linguistics and artificial intelligence. Apply here: apply.interfolio.com/158280 (review starts Dec. 1).

submitted 115 days ago • 0 comments

To researchers doing LLM evaluation: prompting is *not a substitute* for direct probability measurements. Check out the camera-ready version of our work, to appear at EMNLP 2023! (w/ @rplevy.bsky.social) Paper: arxiv.org/abs/2305.13264 Original thread: twitter.com/_jennhu/stat...

submitted 505 days ago • 19 comments