HumorGen: 基于角色蒸馏的大语言模型幽默生成的认知协同
HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
AI总结：
针对大语言模型标准训练目标与幽默所需意外性之间的矛盾，提出认知协同框架，利用六种认知角色合成多样化喜剧视角数据，微调7B参数学生模型，实验表明认知驱动的数据策展比对齐算法或模型规模更关键。
摘要：
幽默生成对大语言模型（LLMs）构成重大挑战，因为其标准训练目标（下一个词预测）与喜剧所需的意外性和不协调性存在固有冲突。为弥合这一差距，我们引入了认知协同框架，这是一种受幽默心理学理论启发的高质量幽默数据生成方法。利用混合思维（MoT）方法，我们部署了六种认知角色（例如荒诞主义者、愤世嫉俗者）来为给定提示合成多样化的喜剧视角。该框架产生了一个基于理论的数据集，我们使用该数据集微调了一个7B参数的学生模型。我们进一步评估了两种对齐策略：直接偏好优化（DPO）和一种离线组相对变体O-GRPO，发现两者均未优于SFT。然而，我们的7B HumorGen模型变体显著优于更大的指令微调基线，并达到顶级开源权重性能，同时与前沿专有系统保持竞争力。这些结果表明，对于幽默生成，认知驱动的数据策展比对齐算法或模型规模更为关键。
英文摘要：
Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective (next-token prediction) inherently conflicts with the surprise and incongruity required for comedy. To bridge this gap, we introduce the Cognitive Synergy Framework, a methodology for generating highquality humor data inspired by psychological theories of humor. Utilizing a Mixtureof-Thought (MoT) approach, we deploy six cognitive personas (e.g., The Absurdist, The Cynic) to synthesize diverse comedic perspectives for a given prompt. This framework produces a theory-grounded dataset, which we use to fine-tune a 7B-parameter student model. We further evaluate two alignment strategies, Direct Preference Optimization (DPO) and an offline group-relative variant O-GRPO, finding that neither improves over SFT. However, our 7B HumorGen model variants significantly outperform larger instruction-tuned baselines and achieve top-tier open-weight performance while remaining competitive with frontier proprietary systems. These results suggest that cognitively driven data curation is more critical than alignment algorithms or model scale for humor generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
