Multimodal LLMs coordinate in reference games through high label overlap that does not depend on specific partner history, succeeding via verbose descriptions rather than compact conventions.
LEEET s-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions
Multimodal LLMs coordinate in reference games through high label overlap that does not depend on specific partner history, succeeding via verbose descriptions rather than compact conventions.