Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis
Open paper
Benchmark
Model
Rank
Results
emotion-recognition-in-conversation-on-meld
PaP (ChatGLM3-6B)
–
Weighted-F1: 65.97
Rank counts only results with a code link.