she/her | Postdoc at McGill Ling / Mila, prev JHU CogSci | language production and morphology!
Coquitlam, BC
Joined September 2017
- Tweets99
- Following204
- Followers195
- Likes500
Bumping the preprint link here bc there were some questions about where it is (buried deep into the thread, haha)
arxiv.org/abs/2607.15175
🦀New preprint! (w/@najoungkim)🦞
Is grammaticality a major organizing principle of NLM representations? We show that many NLMs exhibit abstract rep. separation for grammaticality. We believe this work addresses debates about confounds in measuring model gram. knowledge.
[1/10]
2
225
🦀New preprint! (w/@najoungkim)🦞
Is grammaticality a major organizing principle of NLM representations? We show that many NLMs exhibit abstract rep. separation for grammaticality. We believe this work addresses debates about confounds in measuring model gram. knowledge.
[1/10]
The Q of whether NLMs can have genuine distinctions of grammaticality is debated (Dentella et al., Hu et al. 2023). We believe the methods applied in this work acts as a complementary lens to the study of NLM gram. knowledge, and contribute a new perspective on these debates.
1
1
126
For similar work, we recommend Wang et al. (2026) arxiv.org/abs/2605.05197 and Kryvosheieva et al. (2025) arxiv.org/abs/2512.03676.
Much exciting work is happening in this space and I’ve learned a lot working on this project. Yay! [9/9]
1
1
112
Jane 🐸 retweeted
Excited to share new work on how the brain makes social inferences from visual input! 🧠👯♂️
(With Leyla Isik, Shari Liu, @tianminshu, & @minjaejk!) biorxiv.org/content/10.64898…
Najoung is an amazing mentor and collaborator! Go work with her!!
🫸🫸 (push)
My lab at BU is recruiting PhD students and possibly a postdoc this year!
We study humans & machines, centered around topics like meaning, generalization, evaluation methods and design, and the nature of computation and representation that underlie language and cognition.
🫴🫴
1
4
767
Jane 🐸 retweeted
New paper out in @Psychonomic_Soc!
Using behavioral masked priming and single word reading with concurrent Magnetoencephalography (MEG) recording, we investigate how our brain spots the tiny pieces of words (a.k.a. morphemes)—even when they’re playing hide-and-seek. 👀
Link ⬇️
Jane 🐸 retweeted
📢 New paper 📢
What generalization mechanisms shape the language skills of LLMs?
Prior work has claimed that LLMs learn language via rules.
We revisit the question and find that superficially rule-like behavior of LLMs can be traced to underlying analogical processes.
🧵
One of the highlights of the Fall semester for me is organizing our PhD application mentorship program!!🧑🎓 We offer SOP and general grad school advice, with the goal of supporting first-gen and URM scholars. Got questions? Sign up here: forms.gle/V1tsYLU7L4BezRmD9
Jane 🐸 retweeted
My very first MEG paper is finally accepted for publication in Cortex! 🥳 We investigate the neural profile of early (decomposition) and late stages (recombination) of visual word recognition of inflected prefixed words in Tagalog, an understudied language in neurolinguistics.🧠