2023 · 100 citations · 15 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceKnowledge RepresentationNatural Language ProcessingCharacter ModelingConversational User InterfacesDialogue SystemsLanguage ModelingCharacter GenerationChatbotsConversational AgentsJulius CaesarTrainingUser Simulation
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 memorize their characters and experiences. Experimental results show interesting observations that help build future simulacra of humankind.
15
Training language models to follow instructions with human feedback
Long Ouyang, Jeff Wu, Xu Jiang et al. · arXiv (Cornell University) · 2022 · 4.3K citations · Full text
LLaMA: Open and Efficient Foundation Language Models
Hugo Touvron, Thibaut Lavril, Gautier Izacard et al. · arXiv (Cornell University) · 2023 · 3.9K citations · Full text
arXiv (Cornell University) · 2023 · 2.4K citations · Full text
Generative Agents: Interactive Simulacra of Human Behavior
Joon Sung Park, Joseph O’Brien, Carrie J. Cai et al. · 2023 · 1.5K citations · Full text