Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media

ACL ARR 2025 February Submission5268 Authors

Abstract: Large language models (LLMs) have demonstrated impressive capabilities in role-playing tasks. However, there is limited research on whether LLMs can accurately simulate user behavior in real-world scenarios, such as social media. This requires models to effectively analyze a user's history and simulate their role. In this paper, we introduce \textbf{FineRob}, a novel fine-grained behavior simulation dataset. We collect the complete behavioral history of 1,866 different users on three social media platforms. Each behavior is decomposed into three fine-grained elements: object, type, and content, resulting in 78.6k QA records. Based on FineRob, we identify two dominant reasoning patterns in LLMs' behavior simulation processes and propose the \textbf{OM-CoT} fine-tuning method to enhance the capability. Through comprehensive experiments, we conducted an in-depth analysis of key behavior simulation factors and also demonstrated the effectiveness of the OM-CoT approach\footnote{Code and dataset are available at \url{https://anonymous.4open.science/r/FineRob-791B/}}.

Paper Type: Long

Research Area: Computational Social Science and Cultural Analytics

Research Area Keywords: human behavior analysis;NLP tools for social analysis

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources

Languages Studied: English;Chinese

Submission Number: 5268