HUMORCHAIN：面向可解释多模态幽默生成的理论引导多阶段推理
HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation
把幽默理论中的认知结构显式嵌入多阶段推理链，用于视觉到语言的生成；其「视觉语义解析→理论引导推理→判别器打分」的可解释链条可迁移到需要认知深度或风格化表达的图像描述与多模态生成任务。
原文依据 a theory-guided multi-stage reasoning framework. It integrates visual semantic parsing, humor- and psychology-based reasoning, and a fine-tuned discriminator for humor evaluation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论幽默既是人类的创造性活动，也是一种社会联结机制，长期以来对人工智能生成构成重大挑战。尽管产生幽默需要复杂的认知推理与社会理解，但幽默理论表明幽默遵循可学习的模式与结构，这使得生成模型在理论上有可能隐式习得这些模式与结构。近年来，多模态幽默已成为一种流行的在线交流形式，在 Z 世代群体中尤为普遍，这凸显了构建能够将视觉理解与幽默语言生成相结合的人工智能系统的需求。然而，现有的数据驱动方法缺乏对幽默的显式建模或理论依据，往往生成字面描述，无法捕捉其背后的认知机制，导致生成的图像描述虽然流畅，却缺乏真正的幽默感或认知深度。为解决这一局限，我们提出 HUMORCHAIN（HUmor-guided Multi-step Orchestrated Reasoning Chain for Image Captioning，即幽默引导的多步编排推理链用于图像描述），这是一个理论引导的多阶段推理框架。它整合了视觉语义解析、基于幽默与心理学的推理，以及用于幽默评估的微调判别器，形成一条可解释、可控的认知推理链。据我们所知，这是首个将幽默理论中的认知结构显式嵌入多模态幽默生成的工作，实现了从视觉理解到幽默创作的结构化推理过程。在 Meme-Image-No-Text、Oogiri-GO 和 OxfordTVG-HIC 数据集上的实验表明，HUMORCHAIN 在人类幽默偏好、Elo/BT 分数和语义多样性方面均优于最优基线，证明理论驱动的结构化推理能够使大语言模型生成与人类感知相一致的幽默。
英文原文摘要 1839 字符
Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest that it follows learnable patterns and structures, making it theoretically possible for generative models to acquire them implicitly. In recent years, multimodal humor has become a prevalent form of online communication, especially among Gen Z, highlighting the need for AI systems capable of integrating visual understanding with humorous language generation. However, existing data-driven approaches lack explicit modeling or theoretical grounding of humor, often producing literal descriptions that fail to capture its underlying cognitive mechanisms, resulting in the generated image descriptions that are fluent but lack genuine humor or cognitive depth. To address this limitation, we propose HUMORCHAIN (HUmor-guided Multi-step Orchestrated Reasoning Chain for Image Captioning), a theory-guided multi-stage reasoning framework. It integrates visual semantic parsing, humor- and psychology-based reasoning, and a fine-tuned discriminator for humor evaluation, forming an interpretable and controllable cognitive reasoning chain. To the best of our knowledge, this is the first work to explicitly embed cognitive structures from humor theories into multimodal humor generation, enabling a structured reasoning process from visual understanding to humor creation. Experiments on Meme-Image-No-Text, Oogiri-GO, and OxfordTVG-HIC datasets show that HUMORCHAIN outperforms state-of-the-art baselines in human humor preference, Elo/BT scores, and semantic diversity, demonstrating that theory-driven structured reasoning enables large language models to generate humor aligned with human perception.