Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination

• URL: http://arxiv.org/abs/2504.20643v2
• Date: Sat, 27 Sep 2025 10:06:34 GMT
• Title: Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
• Authors: Moran Mizrahi, Chen Shani, Gabriel Stanovsky, Dan Jurafsky, Dafna Shahaf,
• Abstract summary: We introduce a novel approach that enhances Large Language Models (LLMs) creativity.<n>We apply LLMs for translating between natural language and structured representations, and perform the core creative leap.<n>We demonstrate our approach in the culinary domain with DishCOVER, a model that generates creative recipes.
• Score: 46.79423188943526
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CREward: A Type-Specific Creativity Reward Model [23.62496736021293]
  CREward is a type-specific creativity reward model that spans three creativity axes," geometry, material, and texture.<n>We analyze the correlation between human judgments and predictions by large vision-language models (LVLMs)<n>We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.
  arXiv  Detail & Related papers  (2025-11-25T07:00:42Z)
• CreativityPrism: A Holistic Benchmark for Large Language Model Creativity [64.18257552903151]
  Creativity is often seen as a hallmark of human intelligence.<n>There is still no holistic framework to evaluate their creativity across diverse scenarios.<n>We propose CreativityPrism, an evaluation analysis framework that decomposes creativity into three dimensions: quality, novelty, and diversity.
  arXiv  Detail & Related papers  (2025-10-23T00:22:10Z)
• Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations [47.51585845370428]
  We examine creativity measures including the creativity index, perplexity, syntactic templates, and LLM-as-a-Judge.<n>Our analyses reveal that these metrics exhibit limited consistency, capturing different dimensions of creativity.
  arXiv  Detail & Related papers  (2025-08-07T15:11:48Z)
• Probing and Inducing Combinational Creativity in Vision-Language Models [52.76981145923602]
  Recent advances in Vision-Language Models (VLMs) have sparked debate about whether their outputs reflect combinational creativity.<n>We propose the Identification-Explanation-Implication (IEI) framework, which decomposes creative processes into three levels.<n>To validate this framework, we curate CreativeMashup, a high-quality dataset of 666 artist-generated visual mashups annotated according to the IEI framework.
  arXiv  Detail & Related papers  (2025-04-17T17:38:18Z)
• How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale [47.73894679677285]
  We conduct a computational analysis of 193,353 hackathon projects. We identify means for organizers to foster creativity in hackathons. We explore the use of large language models to augment the evaluation of creative outcomes.
  arXiv  Detail & Related papers  (2025-03-06T10:17:52Z)
• A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models [100.16387798660833]
  Oogiri game is a creativity-driven task requiring humor and associative thinking. LoTbench is an interactive, causality-aware evaluation framework. Results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable.
  arXiv  Detail & Related papers  (2025-01-25T09:11:15Z)
• Steering Large Language Models to Evaluate and Amplify Creativity [7.031631627161492]
  We show that we can leverage this knowledge of how to write creatively in order to better judge what is creative.<n>We take a mechanistic approach that extracts differences in the internal states of an LLM when prompted to respond "boringly" or "creatively"
  arXiv  Detail & Related papers  (2024-12-08T20:28:48Z)
• A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts [2.709166684084394]
  This study proposes a framework called GPS, which employs goals, prompts, and strategies to guide designers to systematically work with an LLM tool for improving the creativity of ideas generated during brainstorming. Our framework, tested through a design example and a case study, demonstrates its effectiveness in stimulating creativity and its seamless LLM tool integration into design practices.
  arXiv  Detail & Related papers  (2024-10-10T13:39:27Z)
• Enhancing Creativity in Large Language Models through Associative Thinking Strategies [9.09055730592338]
  Associative thinking strategies have been found to help humans boost creativity. We investigate whether prompting Large Language Models to connect disparate concepts can augment their creative outputs. Our findings show that leveraging associative thinking techniques can significantly improve the originality of vGPT-4's responses.
  arXiv  Detail & Related papers  (2024-05-09T16:42:29Z)
• Can AI Be as Creative as Humans? [84.43873277557852]
  We prove in theory that AI can be as creative as humans under the condition that it can properly fit the data generated by human creators. The debate on AI's creativity is reduced into the question of its ability to fit a sufficient amount of data.
  arXiv  Detail & Related papers  (2024-01-03T08:49:12Z)
• Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation [19.62178304006683]
  We argue that current interaction paradigms fall short, guiding users towards rapid convergence on a limited set of ideas. We propose a framework that facilitates the structured generation of design space in which users can seamlessly explore, evaluate, and synthesize a multitude of responses.
  arXiv  Detail & Related papers  (2023-10-19T17:53:14Z)
• Telling Creative Stories Using Generative Visual Aids [52.623545341588304]
  We asked writers to write creative stories from a starting prompt, and provided them with visuals created by generative AI models from the same prompt. Compared to a control group, writers who used the visuals as story writing aid wrote significantly more creative, original, complete and visualizable stories. Findings indicate that cross modality inputs by AI can benefit divergent aspects of creativity in human-AI co-creation, but hinders convergent thinking.
  arXiv  Detail & Related papers  (2021-10-27T23:13:47Z)
• Explaining Creative Artifacts [69.86890599471202]
  We develop an inverse problem formulation to deconstruct the products of and compositional creativity into associative chains. In particular, our formulation is structured as solving a traveling salesman problem through a knowledge graph of associative elements.
  arXiv  Detail & Related papers  (2020-10-14T14:32:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.