Characterglm: Customizing Chinese Conversational AI Characters With Large Language Models
Zhou Jinfeng, Chen Zhuang, Wan Dazhen, Wen Bosi, Song Yi, Yu Jifan, Huang Yongkang, Peng Libiao, Yang Jiaming, Xiao Xiyao, Sabour Sahand, Zhang Xiaohan, Hou Wenjing, Zhang Yijia, Dong Yuxiao, Tang Jie, Huang Minlie. Arxiv 2023
[Paper]
In this paper, we present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters. Our CharacterGLM is designed for generating Character-based Dialogues (CharacterDial), which aims to equip a conversational AI system with character customization for satisfying people’s inherent social desires and emotional needs. On top of CharacterGLM, we can customize various AI characters or social agents by configuring their attributes (identities, interests, viewpoints, experiences, achievements, social relationships, etc.) and behaviors (linguistic features, emotional expressions, interaction patterns, etc.). Our model outperforms most mainstream close-source large langauge models, including the GPT series, especially in terms of consistency, human-likeness, and engagement according to manual evaluations. We will release our 6B version of CharacterGLM and a subset of training data to facilitate further research development in the direction of character-based dialogue generation.
Similar Work