Character-LLM: A Trainable Agent for Role-Playing

Yunfan Shao, Linyang Li, Junqi Dai, Xipeng Qiu

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Keywords: human simulacra, LLM

Abstract:

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.\footnote{Code and datasets are public at \url{https://github.com/choosewhatulike/trainable-agents}}

Submission Number: 176