Character-LLM: A Trainable Agent for Role-Playing
This work addresses the challenge of creating more advanced role-playing agents for applications in entertainment or education, though it appears incremental as it builds on existing LLM capabilities.
The authors tackled the problem of training LLMs to simulate specific historical figures by editing profiles as experiences, resulting in a test playground that evaluates whether agents memorize their characters and experiences, with experimental results providing interesting observations for future simulacra.
Large language models (LLMs) can be used to serve as agents to simulate human behaviors, given the powerful ability to understand human instructions and provide high-quality generated texts. Such ability stimulates us to wonder whether LLMs can simulate a person in a higher form than simple human behaviors. Therefore, we aim to train an agent with the profile, experience, and emotional states of a specific person instead of using limited prompts to instruct ChatGPT API. In this work, we introduce Character-LLM that teach LLMs to act as specific people such as Beethoven, Queen Cleopatra, Julius Caesar, etc. Our method focuses on editing profiles as experiences of a certain character and training models to be personal simulacra with these experiences. To assess the effectiveness of our approach, we build a test playground that interviews trained agents and evaluates whether the agents \textit{memorize} their characters and experiences. Experimental results show interesting observations that help build future simulacra of humankind.