RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models

arXiv:2310.00746v2 Announce Type: replace
Abstract: 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) …

abstract art arxiv benchmarking characters cs.ai cs.cl enabling general however interactions language language models large language large language models llms nature optimization playing role state tasks the way training type