Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 41 of its 103 references that are in the map. First posted on arXiv 29 Apr 2025.
Builds on
41 of 103 references.
References · 41
- 2019The Curious Case of Neural Text Degenerationcited by 2,881
- 2018Hierarchical Neural Story Generationcited by 1,182
- 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
- 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
- 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
- 2023State of What Art? A Call for Multi-Prompt LLM Evaluationcited by 299
- 2017Grammar Variational Autoencodercited by 283
- 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
- 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
- 2023Art or Artifice? Large Language Models and the False Promise of Creativitycited by 168
- 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
- 2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
29 more
- 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 121
- 2018Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Imagescited by 118
- 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
- 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
- 2024Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvementscited by 82
- 2024Are Large Language Models Capable of Generating Human-Level Narratives?cited by 78
- 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
- 2022Large-scale Text-to-Image Generation Models for Visual Artists' Creative Workscited by 60
- 2023Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Textcited by 59
- 2024A Survey on Large Language Model Hallucination via a Creativity Perspectivecited by 38
- 2024Benchmarking Language Model Creativity: A Case Study on Code Generationcited by 38
- 2023Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphscited by 35
- 2020RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation Systemcited by 34
- 2023Large Language Models are Complex Table Parserscited by 28
- 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
- 2024HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playingcited by 22
- 2019Syntax-Infused Variational Autoencoder for Text Generationcited by 19
- 2024Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learningcited by 19
- 2024A Simple but Effective Approach to Improve Structured Language Model Output for Information Extractioncited by 16
- 2024Enhancing Creativity in Large Language Models through Associative Thinking Strategiescited by 13
- 2025One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Generation of Humorcited by 12
- 2024FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examinationcited by 10
- 2025FreeBlend: Advancing Concept Blending with Staged Feedback-Driven Interpolation Diffusioncited by 8
- 2022DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept Relationshipscited by 7
- 2024A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughtscited by 4
- 2025SR-LLM: Rethinking the Structured Representation in Large Language Modelcited by 3
- 2025What can large language models do for sustainable food?cited by 3
- 2023Large Language Models as Sous Chefs: Revising Recipes with GPT-3cited by 2
- 202250 Ways to Bake a Cookie: Mapping the Landscape of Procedural Textscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.