arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.00746cs.CLcs.AI
收藏

RoleLLM:基准测试、激发并增强大语言模型的角色扮演能力

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

Beijing University of Posts and Telecommunications(北京邮电大学);The Hong Kong University of Science and Technology(香港科技大学);Beihang University(北京航空航天大学);University of the Chinese Academy of Sciences(中国科学院大学);ETH Zürich(苏黎世联邦理工学院);The Hong Kong Polytechnic University(香港理工大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Shanghai AI Lab(上海人工智能实验室)
Zekun Moore Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zha… 展开作者

Zekun Moore Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Stephen W. Huang, Jie Fu, Junran Peng

AI总结:

针对大语言模型角色扮演能力受闭源和通用训练限制的问题,提出包含四阶段的RoleLLM框架,构建了大规模角色扮演基准数据集,并微调得到中英文模型,实现了媲美GPT-4的角色扮演效果。

摘要:

大语言模型(LLMs)的出现为角色扮演等复杂任务铺平了道路,该任务通过让模型模仿各类角色来提升用户交互体验。然而,当前最先进LLMs的闭源属性及其通用训练方式限制了角色扮演能力的优化。本文提出RoleLLM框架,用于基准测试、激发并增强LLMs的角色扮演能力。该框架包含四个阶段:(1)为100个角色构建角色档案;(2)基于上下文的指令生成(Context-Instruct,用于提取角色专属知识);(3)使用GPT的角色提示(RoleGPT,用于模仿说话风格);(4)角色条件指令微调(RoCIT,用于微调开源模型并实现角色定制)。通过Context-Instruct和RoleGPT,我们构建了RoleBench——首个系统化、细粒度的角色级角色扮演基准数据集,包含168093个样本。此外,在RoleBench上应用RoCIT得到了RoleLLaMA(英文)和RoleGLM(中文),显著提升了角色扮演能力,甚至取得了与RoleGPT(使用GPT-4)相当的效果。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑