Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
This addresses the challenge of enhancing creativity in AI for domains like culinary arts, though it is incremental as it builds on existing structured representation techniques.
The paper tackles the problem of LLMs struggling to produce creative and diverse ideas by introducing a method that recombines structured representations to generate creative recipes, significantly outperforming GPT-4o in novelty and diversity.
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.