用细粒度行为数据训练LLM，模拟社交媒体用户真实行为
Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
- 将用户行为拆解为对象、类型、内容三要素，构建细粒度数据集
- 发现两类主流推理模式，提出OM-CoT方法提升模拟准确率
- 适合研究社交行为建模、角色扮演和大模型可解释性的人群
大型语言模型（LLMs）在角色扮演任务中表现优异，但其在真实场景如社交媒体中模拟用户行为的能力仍缺乏研究。本文提出一种新型细粒度行为模拟数据集FineRob，收集了来自三个社交平台的1,866名用户完整行为历史，每条行为被分解为对象、类型、内容三个细粒度元素，共生成78.6万条问答记录。基于该数据集，我们识别出LLM在行为模拟中的两类主导推理模式，并提出OM-CoT微调方法以增强模型能力。通过全面实验，深入分析行为模拟的关键因素，验证了OM-CoT方法的有效性。代码与数据集已公开。
原文摘要 · Abstract (English)
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}}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。