作者位次 #2/5ACL 2026Poster· Natural Language Processing
Cross-Modal Taxonomic Generalization in (Vision-) Language Models
Tianyang Xu · Marcelo Sandoval-Castañeda · Karen Livescu · Gregory Shakhnarovich · Kanishka Misra
摘要
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 scenario where part of the input comes from a different modality—in our case, in a vision-language model (VLM),...