A retrieval-augmented ensemble of off-the-shelf LLMs predicts perceived emotions in 28 languages without fine-tuning, scoring micro-F1 0.638 on the SemEval-2025 test set.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Empaths at SemEval-2025 Task 11: Retrieval-Augmented Approach to Perceived Emotions Prediction
A retrieval-augmented ensemble of off-the-shelf LLMs predicts perceived emotions in 28 languages without fine-tuning, scoring micro-F1 0.638 on the SemEval-2025 test set.