Retrieving a semantically similar example and voting over paraphrased versions of it improves conversational emotion recognition macro F1 over random in-context examples.
However, the LLM achieves the highest performance with no conversation context provided on the other two datasets, 0.576 in MELD and 0.547 in EmoryNLP
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?
Retrieving a semantically similar example and voting over paraphrased versions of it improves conversational emotion recognition macro F1 over random in-context examples.