Can I read Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media on EtoBox?

Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media by Li, Kun; Dai, Chenwei; Zhou, Wei; Hu, Songlin is a scholarly article available to read on EtoBox.

What is Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media about?

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}}

Author

Li, Kun; Dai, Chenwei; Zhou, Wei; Hu, Songlin

Published

2024

Language

EN