Qing Yao

LMs learn argument-based preferences for dative constructions (preferring recipient first when it’s shorter), being quite consistent with humans. Is this from just memorizing the preferences in their training data? New paper w/ @kanishkamisra, @LAWeissweiler, @kmahowald

Models have preferences like giving inanimate 📦 stuff to animate 👳 Is it that they just saw a lot of such examples in pretraining or is it generalization and deeper understanding? alphaxiv.org/pdf/2503.20850 @qyao23 @kanishkamisra @LAWeissweiler @kmahowald