Author name: Tianyang Xu, Marcelo Sandoval-Castaneda, Karen Livescu, Greg Shakhnarovich, Kanishka Misra

arXiv:2603.07474v2 Announce Type: replace-cross
Abstract: What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenari…