Identity-Driven Hierarchical Role-Playing Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Libo, Wang, Siyuan, Huang, Xuanjing, Wei, Zhongyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911970916040704
author Sun, Libo
Wang, Siyuan
Huang, Xuanjing
Wei, Zhongyu
author_facet Sun, Libo
Wang, Siyuan
Huang, Xuanjing
Wei, Zhongyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Identity-Driven Hierarchical Role-Playing Agents
Sun, Libo
Wang, Siyuan
Huang, Xuanjing
Wei, Zhongyu
Artificial Intelligence
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.
title Identity-Driven Hierarchical Role-Playing Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2407.19412