CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
This addresses the need for character-based dialogue generation to meet social and emotional desires, though it is incremental as it builds on existing models.
The paper tackles the problem of customizing Chinese conversational AI characters by introducing CharacterGLM, a series of models based on ChatGLM with sizes from 6B to 66B parameters, which outperforms mainstream closed-source models like GPT in consistency, human-likeness, and engagement according to manual evaluations.
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.