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 .
ChatHaruhi: Reviving Anime Character in Reality via Large Language Model
The proposed algorithm enhances role-playing chatbots by using improved prompts and character memory to mimic specific fictional characters, demonstrating better performance than baseline methods.
- Year
- 2023
- Venue
- arXiv 2023
- Authors
- 14
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2308.09597ARXIV-DEFAULT
- TL;DR
- Semantic Scholar