Measuring Combinatorial Creativity in Large Language Models and Humans

arXiv:2509.21043 · cs.AI, cs.LG · Submitted 2025-09-25 · Read on arXiv

cs.AI, cs.LG

Submitted: 2025-09-25

Updated: 2026-10-07

Terminology

• Generalization — 2× in this paper · explained in 13 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
• Probing the Creativity of Large Language Models: Can models produce divergent semantic association?
• Generalization and the Rise of System-level Creativity in Science
• LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research
• Two-player Alternate Uses Test: A Controlled Testbed for Interactive Human-AI and Human-Human Co-Creation
• Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist
• COGS: A Compositional Generalization Challenge Based on Semantic Interpretation
• Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks
• Evaluating the Robustness of Analogical Reasoning in Large Language Models
• Large Language Models provide support for the parallelogram theory of analogy
• Cognitive Dark Matter: Measuring What AI Misses
• Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
• Beyond Divergent Creativity: A Human-Based Evaluation of Creativity in Large Language Models
• Spark: A System for Scientifically Creative Idea Generation
• Transformational Creativity in Science: A Graphical Theory
• Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers
• Unlocking LLM Creativity in Science through Analogical Reasoning
• Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
• The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
• A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems