LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play

TL;DR

This paper introduces LLM Discussion, a three-phase framework with role-playing to enhance the creativity of large language models by mimicking human-like discussion and idea exchange, leading to more original responses.

Contribution

The paper presents a novel discussion framework and role-playing technique that significantly improve LLM creativity over existing single and multi-LLM approaches.

Findings

Framework outperforms existing methods in creativity metrics.

Effective in generating more diverse and original responses.

Validated through multiple creativity assessments and human studies.

Abstract

Large language models (LLMs) have shown exceptional proficiency in natural language processing but often fall short of generating creative and original responses to open-ended questions. To enhance LLM creativity, our key insight is to emulate the human process of inducing collective creativity through engaging discussions with participants from diverse backgrounds and perspectives. To this end, we propose LLM Discussion, a three-phase discussion framework that facilitates vigorous and diverging idea exchanges and ensures convergence to creative answers. Moreover, we adopt a role-playing technique by assigning distinct roles to LLMs to combat the homogeneity of LLMs. We evaluate the efficacy of the proposed framework with the Alternative Uses Test, Similarities Test, Instances Test, and Scientific Creativity Test through both LLM evaluation and human study. The results show that our proposed framework outperforms single-LLM approaches and existing multi-LLM frameworks across various creativity metrics. The code is available at https://github.com/lawraa/LLM-Discussion.