@craaaa profile picture
Cara Leong @craaaa

linguistics phd student @ nyu, machine acquisitionist/trainer of models, monday crossword finisher (she/her)

Joined February 2009
  • Tweets 175
  • Following 312
  • Followers 267
23 Photos and videos
Cara Leong retweeted
Byung-Doh Oh@byungdoh
29 Nov 2024
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
29 Nov 2024
📣 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
10
23
3,784
Cara Leong retweeted
Alex Warstadt@a_stadt
4 Nov 2024
👶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?"
8
35
236
25,482
Cara Leong retweeted
Najoung Kim 🫠@najoungkim
4 Nov 2024
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. ⬇️
A logo of tinlab that shows a hedgehog and a tin man chatting about a hedgehog and a tin man chatting about a [...]

ALT A logo of tinlab that shows a hedgehog and a tin man chatting about a hedgehog and a tin man chatting about a [...]

2
21
105
18,154
Cara Leong retweeted
Jack Petty
@jowenpetty
11 Sep 2024
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
1
12
73
12,410
Cara Leong retweeted
Kanishka Misra 🌊@kanishkamisra
21 Aug 2024
🧐🔡🤖 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!
Title of the paper: Generating novel experimental hypotheses from language models: A case study on cross-dative generalization; along with a figure describing our overall method

ALT Title of the paper: Generating novel experimental hypotheses from language models: A case study on cross-dative generalization; along with a figure describing our overall method

2
14
83
14,907
Cara Leong retweeted
Brenden Lake@LakeBrenden
25 Jul 2024
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/5b1… #CogSci2024

Cara Leong@craaaa
19 Jul 2024
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!
3
13
2,411
Cara Leong retweeted
Aaron Mueller@amuuueller
22 Jul 2024
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:
Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks. Aaron Mueller.

ALT Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks. Aaron Mueller.

1
27
137
11,447
Cara Leong retweeted
Kyle Mahowald@kmahowald
19 Jul 2024
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
19 Jul 2024
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!
2
28
2,786
Cara Leong@craaaa
19 Jul 2024
high praise from someone who trained a whopping ninety LMs (read arxiv.org/abs/2403.19827!)

Language Models Learn Rare Phenomena from Less Rare Phenomena: The...

Language models learn rare syntactic phenomena, but the extent to which this is attributable to generalization vs. memorization is a major open question. To that end, we iteratively trained...

arxiv.org
Kanishka Misra 🌊@kanishkamisra
19 Jul 2024
Such a well executed paper! Can totally feel the feeling of training a whopping 125 LMs (but def worth it!)
1
5
660
Cara Leong@craaaa
19 Jul 2024
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!
3
2
17
4,847
Cara Leong@craaaa
19 Jul 2024
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!
1
12
72
13,685
more replies
Cara Leong@craaaa
19 Jul 2024
When dealing with exposure to linguistic input on the scale of millions of words, targeted corpus modification can be used to systematically explore how small changes to the input affect learning. For more, check out the paper: arxiv.org/abs/2407.04593 12/12

1
7
316
Cara Leong@craaaa
19 Jul 2024
@tallinzen is a great mentor; thanks to @jowenpetty @wtimkey8 for listening to early/bad versions of this paper, @kanishkamisra for commiserating over training 125 models, and friends at SCiL 2023 for comments!
9
509
Load more