Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models

TL;DR

This paper presents a reinforcement learning framework that enhances language models' creative and associative thinking abilities, leading to more original and flexible outputs across various generative tasks.

Contribution

It introduces a novel RL-based training method guided by associative thinking principles and divergence metrics to improve AI creativity and adaptability.

Findings

Models generate more original stories and code.

Enhanced abstraction and flexibility in tasks.

Improved coherence and conceptual connectivity.

Abstract

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.