Team hugang11 at SemEval-2026 Task 1: A CoT-SFT, Teacher-Constructed DPO, and Deterministic Post-processing Pipeline for Chinese Humor Generation
The hugang11 system addresses a practical trade-off in creative text generation: models that produce sharper and more stylized jokes often become less stable in output format, and builds a three-stage pipeline that combines chain-of-thought-augmented supervised fine-tuning (CoT-SFT), teacher-constructed direct preference optimization (DPO), and deterministic post-processing.
Gang Hu, Liu Yang, Jing Li
· 1 citation