Year: 2023
Type: preprint
Abstract: Role-playing chatbots built on large language models have drawn interest, but better techniques are needed to enable mimicking specific fictional characters. We propose an algorithm that controls language models via an improved prompt and memories of the character extracted from scripts. We construct ChatHaruhi, a dataset covering 32 Chinese / English TV / anime characters with over 54k simulated dialogues. Both automatic and human evaluations show our approach improves role-playing ability over baselines. Code and data are available at https://github.com/LC1332/Chat-Haruhi-Suzumiya .
Source: arXiv (Cornell University)
Authors: Li, Cheng, Leng, Ziang, Yan, Chenxi, Shen, Junyi, Wang, Hao, MI, Weishi, Fei, Yaying, Feng, Xiaoyang, Yan, Song, Wang, HaoSheng, Zhan, Linkang, Jia, Yaokai, Wu, Pingyu, Sun, Haozhen
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4386044041