烹制创造力:通过结构化重组增强 LLM 创造力
Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
AI总结:
本文提出用 LLM 转换自然语言与结构化表示,并通过认知启发的结构重组提升创意生成,在烹饪任务中以 DishCOVER 显著优于 GPT-4o。
摘要:
大语言模型(LLM)在许多任务上表现出色,却难以产生真正具有创造性且多样化的想法。本文提出一种增强 LLM 创造力的新方法。我们利用 LLM 在自然语言与结构化表示之间进行转换,并通过受认知启发的操作在这些表示上完成核心的创造性跃迁。我们的创造力概念超越了表层 token 级变化;更确切地说,我们重组现有想法的结构化表示,使系统能够有效探索更抽象的想法空间。我们在烹饪领域展示了该方法,提出了生成创意食谱的模型 DishCOVER。实验和领域专家评估表明,我们的输出大多连贯且可行,并在新颖性和多样性方面显著超过 GPT-4o,因此在创造性生成上优于它。我们希望这项工作能激发关于 AI 中结构化创造力的进一步研究。
英文摘要:
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.
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。