Profile avatar
nurikolan.bsky.social
Postdoc, cognitive science & linguistics, Ecole Normale Supérieure https://0xnurl.github.io/
16 posts 105 followers 197 following
Getting Started
Conversation Starter
Posts 7 Comments 10

LLMs are bad theories of human linguistic cognition but can be useful proxies for less bad ones. Here's how and why it might be useful: arxiv.org/abs/2502.07687 Joint paper with @nurikolan.bsky.social, Emmanuel Chemla and @rkatzir.bsky.social

submitted 14 days ago • 0 comments

⭐️🗞️ Accepted to ACL 2024 main conference! #ACL2024NLP Neural nets can in theory learn formal languages such as aⁿbⁿ & Dyck. Yet no one ever finds such nets using standard techniques. Why? We suggest that the culprit might have been the objective function all along 👇 arxiv.org/abs/2402.10013

submitted 254 days ago • 0 comments

🧪🗞️ New paper with Emmanuel Chemla and @rkatzir.bsky.social: Neural nets offer good approximation but consistently fail to generalize perfectly, even when perfect solutions are proved to exist. We check whether the culprit might be their training objective. arxiv.org/abs/2402.10013

submitted 375 days ago • 1 comment

🎲 GPTs can't count – new simple demo of LLMs' very partial arithmetics. github.com/0xnurl/gpts-...

submitted 439 days ago • 0 comments

Douglas Hofstadter on toy tasks, in Waking Up from the Boolean Dream, 1982

submitted 461 days ago • 0 comments

⚡ 🗞️ New up-to-date version of Large Language Models and the Argument from the Poverty of the Stimulus, work with Emmanuel Chemla and @rkatzir.bsky.social: ling.auf.net/lingbuzz/006...

submitted 463 days ago • 1 comment

How well can neural networks generalize from how little data? New work with Emmanuel Chemla and Roni Katzir: Benchmark: github.com/taucompling/... Paper: aclanthology.org/2023.clasp-1... 🧵

submitted 513 days ago • 1 comment