@tallinzen @xuanalogue non-native speakers when their linguistics professors ask them for acceptability judgments 🫠
English
Cara Leong
175 posts
Cara Leong
@craaaa
linguistics phd student @ nyu, machine acquisitionist/trainer of models, monday crossword finisher (she/her)
Katılım Şubat 2009
312 Takip Edilen261 Takipçiler
I don't understand the point of asking mainstream LLMs for syntactic acceptability judgments anymore. We just asked about some island violation and it gave the right answer and then the reasoning trace helpfully said something like "according to Ross (1967), this sentence violates the complex NP island constraint, so I should say it is ungrammatical". OK, yes, good job.
English
anyone have recs for good coffee shops to work from in nyc / working spaces in general? around nyu is a plus!
English
Cara Leong retweetledi
Submissions for the 2025 Workshop on Cognitive Modeling and Computational Linguistics are due Feb. 16
I humbly request your help with spreading the word
CMCL workshop@CMCL_workshop
📣 We are happy to share that CMCL 2025 will be co-located with NAACL in New Mexico! 👉The call for papers is out cmclorg.github.io/CfP SAVE THE DATES, and submit your work! ‼️ Paper submission deadline: Feb 16, 2025 🗓 May 3 or 4, 2025: Workshop (TBA) @naacl @naaclmeeting
English
Cara Leong retweetledi
👶NEW PAPER🪇
Children are better at learning a second language (L2) than adults. In a new paper (led by the awesome Ionut Constantinescu) we ask:
1. "Do LMs also have a 'Critical Period' (CP) for language acquisition?" and
2. "What can LMs tell us about the CP in humans?"
English
Cara Leong retweetledi
tinlab at Boston University (with a new logo! 🪄) is recruiting PhD students for F25 and/or a postdoc! Our interests include meaning, generalization, evaluation design, and the nature of computation/representation underlying language and cognition, in both humans and machines. ⬇️
English
dall-e failed to pass my compositional generalization test tsk tsk
xuan (ɕɥɛn / sh-yen)@xuanalogue
@SurenVynn @confucian_the perhaps I should have learned to generalize from the existence of light and dark chai tow kway
English
Cara Leong retweetledi
How does pretraining on source code impact performance on other tasks? In a new preprint we (@TalLinzen and @vansteenkiste_s) show that it can improve compositional generalization and can help on other tasks, though the impact isn’t _always_ positive. arxiv.org/abs/2409.04556
English
🧐🔡🤖 Can LMs/NNs inform CogSci? This question has been (re)visited by many people across decades.
@najoungkim and I contribute to this debate by using NN-based LMs to generate novel experimental hypotheses which can then be tested with humans!
English
Finally, we are grateful to many folks for their valuable feedback and support:
English
@jowenpetty use your research funds to get a blackboard for the office
English
this is also critical edtech infra
Jackson Petty@jowenpetty
we’ve already perfected educational technology
English
@JulieKallini @isabelpapad @rljfutrell @kmahowald @ChrisGPotts Congrats on the paper (and the color palette)!!!
English
Honored to receive Best Paper Award at #ACL2024 for “Mission: Impossible Language Models”! 🚀
Big thank you to my co-authors @isabelpapad @rljfutrell @kmahowald @ChrisGPotts!
English
Cara Leong retweetledi
Cara is presenting her paper today (poster P1-E-27), asking whether LLMs can simulate expertise effects just by telling the system "you are an expert in birds" or "an expert in dogs". Check it out! escholarship.org/uc/item/5b1328… #CogSci2024
Cara Leong@craaaa
Excited to be going to my first @cogsci_soc next week! I'll be presenting a poster (with @LakeBrenden) about whether multimodal LMs behave like human experts, and would love to meet new (and old) friends!
English
Cara Leong retweetledi
What is cause and effect? What is a “mechanism”? And how do answers to these questions affect interpretability research?
📜 New preprint! 📜 Two key challenges for causal/mechanistic interpretability, and ways forward. To be presented at the mech interp workshop at #ICML2024:
English
English
@lambdaviking @lltjuatja need new passtime that involves playing pickle ball while eating pickles
English
Cara Leong retweetledi
This work is a great example of how un-blackbox-like and linguistically interesting language models can be when the training data is manipulated!
Cara Leong@craaaa
New preprint! How can we test hypotheses about learning that rely on exposure to large amounts of data? No babies no problem: Use language models as models of learning + 🎯targeted modifications 🎯 of language models’ training corpora!
English
@craaaa that “ninety” is going to change in a few days… 👀
English
high praise from someone who trained a whopping ninety LMs (read arxiv.org/abs/2403.19827!)
Kanishka Misra 🌊@kanishkamisra
Such a well executed paper! Can totally feel the feeling of training a whopping 125 LMs (but def worth it!)
English
@katiedimartin need to cover your bases so that you get retweets on your paper thread
English