EmoBench-M is a new multimodal benchmark evaluating 27 MLLMs on foundational emotion recognition, conversational understanding, and socially complex emotion analysis, revealing substantial gaps to human performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models
EmoBench-M is a new multimodal benchmark evaluating 27 MLLMs on foundational emotion recognition, conversational understanding, and socially complex emotion analysis, revealing substantial gaps to human performance.