用结构化重组提升大模型创造力，生成更新颖多样的菜谱。
Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
- 将自然语言转为结构化表示，再通过认知启发式操作重组。
- 在厨艺领域生成的菜谱比GPT-4o更具新颖性和多样性。
- 适合对创意生成、结构化推理感兴趣的AI研究者。
大语言模型在诸多任务中表现优异，但在生成真正原创且多样化的想法方面仍显不足。本文提出一种新方法，通过将自然语言与结构化表示相互转换，并在这些表示上进行受认知启发的操作，实现核心创意突破。本方法超越简单的词元层面变化，而是重组已有想法的结构化表示，使系统能探索更抽象的想法空间。我们在厨艺领域验证该方法，构建了名为DishCOVER的模型，用于生成创意菜谱。实验与领域专家评估表明，我们的输出大多连贯可行，其新颖性与多样性显著优于GPT-4o，证明在创造性生成任务中具有更强表现。我们希望此工作能激发更多关于人工智能结构化创造力的研究。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCOVER, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI.
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。