让AI笑话更懂语境，通过规划与文化推理生成更贴切的幽默。
HumorPlanSearch: Structured Planning and HuCoT for Contextual AI Humor
- 分步规划+文化思维链，精准匹配不同情境的笑点策略。
- 综合评分提升15.4%，在9个主题上获13位评委一致认可。
- 适合研究情感计算、人机互动或内容生成的开发者参考。
基于大语言模型的自动幽默生成常因缺乏语境而显得平淡或失当，因为幽默高度依赖听众的文化背景、心理状态和即时情境。本文提出HumorPlanSearch，一个模块化流程：(1) 通过计划-搜索实现多样化的主题定制策略；(2) 使用幽默思维链（HuCoT）模板捕捉文化与风格化推理；(3) 利用知识图谱检索并复用过往有效策略；(4) 通过语义嵌入过滤重复内容；(5) 基于迭代判别器的修订循环。为评估语境敏感性与喜剧质量，提出幽默生成评分（HGS），融合直接评分、多角色反馈、成对胜率与主题相关性。在九个主题上，13名人类评委参与实验，完整流程（含知识图谱+修订）使平均HGS提升15.4%（p < 0.05），显著优于强基线。该方法在策略规划到多信号评估全链路强调语境，推动AI幽默向更连贯、自适应与文化契合的方向发展。
原文摘要 · Abstract (English)
Automated humor generation with Large Language Models (LLMs) often yields jokes that feel generic, repetitive, or tone-deaf because humor is deeply situated and hinges on the listener's cultural background, mindset, and immediate context. We introduce HumorPlanSearch, a modular pipeline that explicitly models context through: (1) Plan-Search for diverse, topic-tailored strategies; (2) Humor Chain-of-Thought (HuCoT) templates capturing cultural and stylistic reasoning; (3) a Knowledge Graph to retrieve and adapt high-performing historical strategies; (4) novelty filtering via semantic embeddings; and (5) an iterative judge-driven revision loop. To evaluate context sensitivity and comedic quality, we propose the Humor Generation Score (HGS), which fuses direct ratings, multi-persona feedback, pairwise win-rates, and topic relevance. In experiments across nine topics with feedback from 13 human judges, our full pipeline (KG + Revision) boosts mean HGS by 15.4 percent (p < 0.05) over a strong baseline. By foregrounding context at every stage from strategy planning to multi-signal evaluation, HumorPlanSearch advances AI-driven humor toward more coherent, adaptive, and culturally attuned comedy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。