Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
This work addresses the need for accurate behavior simulation in social media applications, but it is incremental as it builds on existing role-playing LLM research with a new dataset and method.
The paper tackles the problem of simulating user behavior on social media using large language models by introducing FineRob, a dataset with 78.6k QA records from 1,866 users, and proposes the OM-CoT method to enhance simulation capabilities, demonstrating its effectiveness through experiments.
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 distinct users across 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 conduct an in-depth analysis of key factors of behavior simulation and also demonstrate the effectiveness of OM-CoT approach\footnote{Code and dataset are available at \url{https://github.com/linkseed18612254945/FineRob}}