This work is a great example of how un-blackbox-like and linguistically interesting language models can be when the training data is manipulated!

Excited to be going to my first CogSci Society next week! I'll be presenting a poster (with Brenden Lake) about whether multimodal LMs behave like human experts, and would love to meet new (and old) friends!

high praise from someone who trained a whopping ninety LMs (read arxiv.org/abs/2403.19827!)

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:

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

🧐🔡🤖 Can LMs/NNs inform CogSci? This question has been (re)visited by many people across decades. Najoung Kim 🫠 and I contribute to this debate by using NN-based LMs to generate novel experimental hypotheses which can then be tested with humans!

How does pretraining on source code impact performance on other tasks? In a new preprint we (@TalLinzen and Sjoerd van Steenkiste) 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

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. ⬇️

👶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?"

Submissions for the 2025 Workshop on Cognitive Modeling and Computational Linguistics are due Feb. 16 I humbly request your help with spreading the word