2 papers
cs.CL2026
Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions
Po-Ya Angela Wang, Chinmaya Mishra, Aslı Özyürek +2
Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific conventions grounded in shared interaction history. Pri…
cs.CL2025
Using Perspectival Words Is Harder Than Vocabulary Words for Humans and Even More So for Multimodal Language Models
Dota Tianai Dong, Yifan Luo, Po-Ya Angela Wang +2
Multimodal language models (MLMs) increasingly demonstrate human-like communication, yet their use of everyday perspectival words remains poorly understood. To address this gap, we…