Cooking up creativity: Enhancing LLM creativity through structured recombination
Moran Mizrahi
2025Computer science - computation and language, computer science - artificial intelligence, computer science - machine learning
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 exis
Relevance Assessment
Research Gap
Notes
Notes are automatically saved as you type
Tags
Human-In-The-Loop › Autonomous GenerationCreativity Frameworks › Logical CreativityCreativity Frameworks › Computational CreativityCreativity Evaluation Methods › Automatic MetricsCreativity Evaluation Methods › Creativity-Specific EvaluationLevel of Analysis › Document-LevelCreativity Evaluation Methods › Human EvaluationProprietary Models › OpenAI ChatGPTModel Scale › Large (>32B)Relationship to Creativity › ExplicitResearch Focus › Prompt EngineeringResearch Focus › Architectural Research
Search Queries
Paper ID: e1dd8883-5df0-430b-acb1-89e059ca37d6Added: 10/26/2025