Identity-Driven Hierarchical Role-Playing Agents

TL;DR

This paper introduces a Hierarchical Identity Role-Playing Framework (HIRPF) for large language models, enabling more precise and flexible role-playing by combining multiple identities, with promising results in social simulation.

Contribution

The paper proposes a novel hierarchical framework based on identity theory for role-playing, along with a new dataset and evaluation benchmark to improve identity-level role simulation.

Findings

Effective in modeling identity-level role simulation

Demonstrates potential in social simulation applications

Outperforms existing methods in precision and flexibility

Abstract

Utilizing large language models (LLMs) to achieve role-playing has gained great attention recently. The primary implementation methods include leveraging refined prompts and fine-tuning on role-specific datasets. However, these methods suffer from insufficient precision and limited flexibility respectively. To achieve a balance between flexibility and precision, we construct a Hierarchical Identity Role-Playing Framework (HIRPF) based on identity theory, constructing complex characters using multiple identity combinations. We develop an identity dialogue dataset for this framework and propose an evaluation benchmark including scale evaluation and open situation evaluation. Empirical results indicate the remarkable efficacy of our framework in modeling identity-level role simulation, and reveal its potential for application in social simulation.