A 7B LLM fine-tuned on humor data generated via six cognitive personas and Mixture-of-Thought outperforms larger instruction-tuned baselines and competes with proprietary models.
arXiv preprint arXiv:2509.21164 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gains across 15 benchmarks.
citing papers explorer
-
HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
A 7B LLM fine-tuned on humor data generated via six cognitive personas and Mixture-of-Thought outperforms larger instruction-tuned baselines and competes with proprietary models.
-
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gains across 15 benchmarks.