RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
This work addresses the need for improved role-playing abilities in LLMs to enhance user interactions, representing an incremental advancement through systematic benchmarking and fine-tuning.
The paper tackles the problem of limited role-playing optimization in large language models (LLMs) due to their closed-source nature and general-purpose training, introducing RoleLLM, a framework that creates RoleBench, a benchmark dataset with 168,093 samples, and enhances models like RoleLLaMA and RoleGLM to achieve results comparable to GPT-4.
The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters. However, the closed-source nature of state-of-the-art LLMs and their general-purpose training limit role-playing optimization. In this paper, we introduce RoleLLM, a framework to benchmark, elicit, and enhance role-playing abilities in LLMs. RoleLLM comprises four stages: (1) Role Profile Construction for 100 roles; (2) Context-Based Instruction Generation (Context-Instruct) for role-specific knowledge extraction; (3) Role Prompting using GPT (RoleGPT) for speaking style imitation; and (4) Role-Conditioned Instruction Tuning (RoCIT) for fine-tuning open-source models along with role customization. By Context-Instruct and RoleGPT, we create RoleBench, the first systematic and fine-grained character-level benchmark dataset for role-playing with 168,093 samples. Moreover, RoCIT on RoleBench yields RoleLLaMA (English) and RoleGLM (Chinese), significantly enhancing role-playing abilities and even achieving comparable results with RoleGPT (using GPT-4).