Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models
This addresses the problem of improving creative thinking in AI for applications such as story writing and code generation, though it appears incremental as it builds on existing RL and creativity metrics.
The paper tackled enhancing language models' creativity by using reinforcement learning guided by associative thinking principles, resulting in models that generated more original and coherent stories and showed improved abstraction and flexibility in tasks like programming and data visualization.
Associative thinking--the ability to connect seemingly unrelated ideas--is a foundational element of human creativity and problem-solving. This paper explores whether reinforcement learning (RL) guided by associative thinking principles can enhance a model's performance across diverse generative tasks, including story writing, code generation, and chart creation. We introduce a reinforcement learning framework that uses a prompt-based evaluation mechanism, incorporating established divergent thinking metrics from creativity research. A base language model is fine-tuned using this framework to reward outputs demonstrating higher novelty through higher degrees of conceptual connectivity. Interestingly, the experimental results suggest that RL-based associative thinking-trained models not only generate more original and coherent stories but also exhibit improved abstraction and flexibility in tasks such as programming and data visualization. Our findings provide initial evidence that modeling cognitive creativity principles through reinforcement learning can yield more adaptive and generative AI.