Lightnews — Scholar-powered news

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Jun 3

🌟🌟This paper will appear at ACL 2025 (@aclmeeting.bsky.social)! New updated version is on arXiv: arxiv.org/pdf/2505.07659 🌟🌟

9

Reposted by Ethan Gotlieb Wilcox

Sasha Boguraev @ COLM @sashaboguraev.bsky.social · May 27

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!

🧵👇!

1 6 23

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

We see this project as in line with some other recent papers seeking to cast typological variation in information-theoretic terms, with shout-outs to Michaela Socolof, @postylem.bsky.social @futrell.bsky.social (aclanthology.org/2022.coling-...) and Julius Steuer (aclanthology.org/2023.sigtyp-...)

Measuring Morphological Fusion Using Partial Information Decomposition

Michaela Socolof, Jacob Louis Hoover, Richard Futrell, Alessandro Sordoni, Timothy J. O’Donnell. Proceedings of the 29th International Conference on Computational Linguistics. 2022.

aclanthology.org

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

⭐ ⭐This paper also makes several technical contributions to the mixed-pair mutual information estimation pipeline of Wolf et al., (aclanthology.org/2023.emnlp-m...). Shout out to @cuiding.bsky.social for all her hard work on this aspect of the paper! ⭐⭐

Quantifying the redundancy between prosody and text

Lukas Wolf, Tiago Pimentel, Evelina Fedorenko, Ryan Cotterell, Alex Warstadt, Ethan Wilcox, Tamar Regev. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

aclanthology.org

1 2

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

✅In line with our prediction, we find that mutual information is higher in tonal languages than in non-tonal languages. BUT, the way one represents context is important. When full sentential context is taken into account (mBERT and mGPT), the distinction collapses.

1 1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

🌏🌍We test this prediction by estimating mutual information in an audio dataset of 10 different languages across 6 language families. 🌏🌍

1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

We propose a way to do so using …📡information theory.📡 In tonal languages, pitch reduces uncertainty about lexical identity, therefore, the mutual information between pitch and words should be higher.

1 1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

🌐But there are intermediate languages, which have lexically contrastive tone, but only sporadically, making some linguists doubt the tonal/non-tonal dichotomy. So, how can we measure how “tonal” a language is? 🧐🧐

1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

🌏 Different languages use pitch in different ways. 🌏 “Tonal” languages, like Cantonese, use it to make lexical distinctions. 📖 While others, like English, use it for other functions, like marking whether or not a sentence is a question. ❓

1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · May 13

⭐🗣️New preprint out: 🗣️⭐ “Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent” with @cuiding.bsky.social , Giovanni Acampa, @tpimentel.bsky.social , @alexwarstadt.bsky.social ,Tamar Regev: arxiv.org/abs/2505.07659

Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent

This paper argues that the relationship between lexical identity and prosody -- one well-studied parameter of linguistic variation -- can be characterized using information theory. We predict that lan...

arxiv.org

1 5 11

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

I’ll also use this as a way to plug human-scale language modeling in the wild: This year’s BabyLM eval pipeline was just released last week at github.com/babylm/evalu.... For more info on BabyLM head to babylm.github.io

GitHub - babylm/evaluation-pipeline-2025

Contribute to babylm/evaluation-pipeline-2025 development by creating an account on GitHub.

github.com

3

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

Couldn’t be happier to have co-authored this will a stellar team, including: Michael Hu, @amuuueller.bsky.social, @alexwarstadt.bsky.social, @lchoshen.bsky.social, Chengxu Zhuang, @adinawilliams.bsky.social, Ryan Cotterell, @tallinzen.bsky.social

1 1 3

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

This version includes 😱New analyses 😱new arguments 😱 and a whole new “Looking Forward” section! If you’re interested in what a team of (psycho) computational linguists thinks the future will hold, check out our brand new Section 8!

1 1

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 3 18

Reposted by Ethan Gotlieb Wilcox

Cui Ding @cuiding.bsky.social · Mar 7

Excited to share our preprint "Using MoTR to probe agreement errors in Russian"! w/ Metehan Oğuz, @wegotlieb.bsky.social, Zuzanna Fuchs Link: osf.io/preprints/ps...
1- We provide moderate evidence that processing of agreement errors is modulated by agreement type (internal vs external agr.)

OSF

osf.io

1 1 3

Reposted by Ethan Gotlieb Wilcox

John Mansfield @johnbasil.bsky.social · Feb 27

Me and @wegotlieb.bsky.social were recently invited to write a wide-ranging reflection on the current state of linguistic theory and methodology.
A draft is up here. For anyone interested in thinking big about linguistics, we'd be happy to hear your thoughts!
arxiv.org/abs/2502.18313
#linguistics

Looking forward: Linguistic theory and methods

This chapter examines current developments in linguistic theory and methods, focusing on the increasing integration of computational, cognitive, and evolutionary perspectives. We highlight four major ...

arxiv.org

2 14

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

⚖️📣This paper was a big departure from my typical cognitive science fare, and so much fun to write! 📣⚖️ Thank you to @bwal.bsky.social and especially to @kevintobia.bsky.social for their legal expertise on this project!

1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

On the positive side, we suggest that LLMs can serve a role as “dialectic” partners 🗣️❔🗣️ helping judges and clerks strengthen their arguments, as long as judicial sovereignty is maintained 👩‍⚖️👑👩‍⚖️

1 2

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

⚖️ We also show, through demonstration, that it’s very easy to engineer prompts that steer models toward one’s desired interpretation of a word or phrase. 📖Prompting is the new “dictionary shopping” 😬 📖 😬

1 1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

🏛️We identify five “myths” about LLMs which, when dispelled, reveal their limitations as legal tools for textual interpretation. To take one example, during instruction tuning, LLMs are trained on highly structured, non-natural inputs.

1 1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

We argue no! 🙅‍♂️ While LLMs appear to possess excellent language capabilities, they should not be used as references for “ordinary language use,” at least in the legal setting. ⚖️ The reasons are manifold.

1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

🏛️Last year a U.S. judge queried Chat GPT to help with their interpretation of “ordinary meaning,” in the same way one might use a dictionary to look up the ordinary definition of a word 📖 … But is it the same?

1

Ethan Gotlieb Wilcox @wegotlieb.bsky.social · Feb 19

📣 New Paper ⚖️🧑‍⚖️🏛️ Large Language Models for Legal Interpretation? Don't Take Their Word for It 👩‍⚖️🏛️⚖️ with @bwal.bsky.social , @complingy.bsky.social Amir Zeldes, and @kevintobia.bsky.social papers.ssrn.com/sol3/papers....

Large Language Models for Legal Interpretation? Don't Take Their Word for It

<p><span>Recent breakthroughs in statistical language modeling have impacted countless domains, including the law. Chatbot applications such as ChatGPT, Claude,

papers.ssrn.com

1 3 13