让大模型学会像人一样讲笑话，靠的是结构化思维跳跃和外部知识注入。
Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
- 通过指令演化与强化学习，构建多跳推理链条来理解笑点逻辑。
- 在 humor 生成任务上，模型判断力与创造力均显著提升。
- 适合研究AI幽默、创意生成或大模型认知机制的学者参考。
幽默曾被视为人类独有的能力，因其高度依赖文化语境，且需多跳推理，每一步都需合理依据。尽管如 GPT-o1 等模型在反思与纠错逻辑推理方面取得进展，但在幽默生成上仍表现不足，主要因创造性思维中知识图谱稀疏，难以支撑多跳推理。为此，本文提出更鲁棒的幽默推理框架 LoL，通过引入外部信息缓解知识图谱稀疏问题。第一阶段，采用自动指令演化方法，挖掘幽默背后的深层思维过程；设计以判断为导向的指令，动态补充并更新稀疏知识图谱。第二阶段，利用 GPT-4o 提取在线生成响应的推理逻辑，并通过强化学习重新引入外部知识，辅助模型进行逻辑推理与人类偏好学习。实验表明，该双阶段流程能有效提升模型的判断力与生成能力，深化对大语言模型（LLMs）创造潜力的理解，并为跨领域创新应用提供新路径。
原文摘要 · Abstract (English)
Humor is previously regarded as a gift exclusive to humans for the following reasons. Humor is a culturally nuanced aspect of human language, presenting challenges for its understanding and generation. Humor generation necessitates a multi-hop reasoning process, with each hop founded on proper rationales. Although many studies, such as those related to GPT-o1, focus on logical reasoning with reflection and correction, they still fall short in humor generation. Due to the sparsity of the knowledge graph in creative thinking, it is arduous to achieve multi-hop reasoning. Consequently, in this paper, we propose a more robust framework for addressing the humor reasoning task, named LoL. LoL aims to inject external information to mitigate the sparsity of the knowledge graph, thereby enabling multi-hop reasoning. In the first stage of LoL, we put forward an automatic instruction-evolution method to incorporate the deeper and broader thinking processes underlying humor. Judgment-oriented instructions are devised to enhance the model's judgment capability, dynamically supplementing and updating the sparse knowledge graph. Subsequently, through reinforcement learning, the reasoning logic for each online-generated response is extracted using GPT-4o. In this process, external knowledge is re-introduced to aid the model in logical reasoning and the learning of human preferences. Finally, experimental results indicate that the combination of these two processes can enhance both the model's judgment ability and its generative capacity. These findings deepen our comprehension of the creative capabilities of large language models (LLMs) and offer approaches to boost LLMs' creative abilities for cross-domain innovative applications.
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。