Training a generative classifier to output an LLM-generated reasoning before the emotion label improved emotion classification accuracy from 49.7% to 58.4% on the dair-ai/emotion test set.
Meta llama 3.2: A 1.4t parameter class of language models
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
-
Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning
Training a generative classifier to output an LLM-generated reasoning before the emotion label improved emotion classification accuracy from 49.7% to 58.4% on the dair-ai/emotion test set.