Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913597016244224 |
|---|---|
| author | Li, Kun Dai, Chenwei Zhou, Wei Hu, Songlin |
| author_facet | Li, Kun Dai, Chenwei Zhou, Wei Hu, Songlin |
| contents | 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}} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03148 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media Li, Kun Dai, Chenwei Zhou, Wei Hu, Songlin Computation and Language Artificial Intelligence Computers and Society 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}} |
| title | Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2412.03148 |