Persona-based Mixture-of-Thought data curation lets a 7B student outperform larger models on humor generation, while DPO and O-GRPO add no gain over SFT.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
Persona-based Mixture-of-Thought data curation lets a 7B student outperform larger models on humor generation, while DPO and O-GRPO add no gain over SFT.