CharacterGLM: Customizing Social Characters with Large Language Models
Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Pei Ke
Abstract
Character-based dialogue (CharacterDial) has become essential in the industry (e.g., Character.AI), enabling users to freely customize social characters for social interactions. However, the generalizability and adaptability across various conversational scenarios inherent in customizing social characters still lack public industrial solutions. To address these challenges, by dissecting well-rounded social characters composed of both inherent social profiles and external social behaviors, we manually collect a large-scale Chinese corpus featuring characters with diverse categories and behaviors, and develop CharacterGLM models alongside well-designed refinement methods. Extensive experiments show that CharacterGLM outperforms most popular open- and closed-source LLMs and performs comparably to GPT-4. We will release our data and models for local development and deployment.
BibTeX
@inproceedings{zhou-etal-2024-characterglm,
title = "{C}haracter{GLM}: Customizing Social Characters with Large Language Models",
author = "Zhou, Jinfeng and
Chen, Zhuang and
Wan, Dazhen and
Wen, Bosi and
Song, Yi and
Yu, Jifan and
Huang, Yongkang and
Ke, Pei and
Bi, Guanqun and
Peng, Libiao and
Yang, JiaMing and
Xiao, Xiyao and
Sabour, Sahand and
Zhang, Xiaohan and
Hou, Wenjing and
Zhang, Yijia and
Dong, Yuxiao and
Wang, Hongning and
Tang, Jie and
Huang, Minlie",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.107/",
doi = "10.18653/v1/2024.emnlp-industry.107",
pages = "1457--1476"
}