ChatHaruhi: Reviving Anime Character in Reality via Large Language Model
This work addresses the need for better role-playing chatbots for anime and TV fans, though it is incremental as it builds on existing techniques with a new dataset and method.
The authors tackled the problem of enabling large language models to better mimic specific fictional characters by proposing an algorithm that uses improved prompts and character memories extracted from scripts, resulting in improved role-playing ability over baselines as shown in automatic and human evaluations.
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 .