Abstract

This position paper argues that synthetic personas used in Large Language Models (LLM) social simulations need explicit grounding. By grounding, we mean that researchers should state where persona information comes from, what social actor or population it is meant to represent, what evidence supports it, and what kinds of simulation claims it can justify. Without such grounding, persona-based simulations risk treating appearance of plausible descriptions or vivid narratives as evidence of realism. We identify several recurring failure modes that explicit grounding can help expose, and argue that these failures should not be diagnosed only after simulation results are produced; they should be addressed at the level of persona construction and reporting. We conclude by proposing lightweight reporting standards for persona provenance, construction process, selection or sampling logic, internal consistency checks, model enactment checks, and intended inference.

Date

2026

Authors

Yucheng Lu, Xiaoyi Liu, Heming Liu, Hanwen Xing, Shirley Huang, Guanghui Min, Zhengyang Shan, My Chiffon Nguyen, Ishan Gupta, Zonglin Di, Qianfeng Wen, Yifan Simon Liu, Ruoqi Gao, Yilan Fan, Jianheng Hou, Brihi Joshi, Muhammad Ahmed Mohsin, Yunze Xiao, Keyang Xuan, Hannah Collison, Jintao Huang, Jiatong Li, Sankalp Jajee, Yunhan Zhao, Bing Hu, Zhiwei Zhang, Sky Ng, Xupeng Chen, Weihang Xiao, Aravind Mohan, Bolun Sun, Yunshu Wu, Yuanda Xu, Yun Shen, Zheyuan Deng, Xincheng Tan, Qianyu Julie Zhu, Dianzhuo Wang, Yijun Wang, Runyu Zhang, Yixuan He, Xiaomin Li, Yuexing Hao

Conference

Second Workshop on Social Simulation with LLMS: Fidelity in Applications