New paper with @romanfeiman.bsky.social's lab, special to me given the inspiration from a parenting observation, when my then-2yo would regularly (and sensibly) confuse "anything" with "nothing"; turns out she was not alone and we can learn something about negative concord and semantic variation too

Linguists, encourage potential postdocs who are AI/computationally focused to apply to these fellowships at the Kempner Institute!

Why can’t LMs solve puzzles about the number systems of languages, when they can solve really complex math problems? Our new paper, led by @antararb.bsky.social looks at why this intersection of language and math is difficult, and what this means for LM reasoning! arxiv.org/abs/2506.13886

We are super excited to be hosting SALT 35 next week! Whether or not you can make it to the Harvard campus in Cambridge MA next week, you can preview the full program (with links to OSF repositories with abstracts, etc) here: saltconf.github.io/salt35/confe...

Hi semantics friends, this is the SALT 35 organizers at Harvard taking over from our SALT 34 at Rochester colleagues! We begin with the hopefully welcome news that this year's abstract submission deadline is now this Friday (Dec. 20), extended from this Wed Dec. 18: saltconf.github.io/salt35/