A cue-coverage reward plus a modality-token KL penalty makes multimodal emotion-reasoning models cite more real visual/audio evidence and hallucinate less, with reported SoTA on emotion benchmarks.
arXiv preprint arXiv:2409.05015 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Omni-Perception Policy Optimization for Multimodal Emotion Reasoning
A cue-coverage reward plus a modality-token KL penalty makes multimodal emotion-reasoning models cite more real visual/audio evidence and hallucinate less, with reported SoTA on emotion benchmarks.