@inproceedings{wang-etal-2025-sociobench,
    title = "{S}ocio{B}ench: Modeling Human Behavior in Sociological Surveys with Large Language Models",
    author = "Wang, Jia  and
      Zhao, Ziyu  and
      Ni, Tingjuntao  and
      Wei, Zhongyu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1335/",
    pages = "26268--26300",
    ISBN = "979-8-89176-332-6",
    abstract = "Large language models (LLMs) show strong potential for simulating human social behaviors and interactions, yet lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes. To bridge this gap, we introduce SocioBench{---}a comprehensive benchmark derived from the annually collected, standardized survey data of the \textit{International Social Survey Programme (ISSP)}. The benchmark aggregates over 480,000 real respondent records from more than 30 countries, spanning 10 sociological domains and over 40 demographic attributes. Our experiments indicate that LLMs achieve only 30{--}40{\%} accuracy when simulating individuals in complex survey scenarios, with statistically significant differences across domains and demographic subgroups. These findings highlight several limitations of current LLMs in survey scenarios, including insufficient individual-level data coverage, inadequate scenario diversity, and missing group-level modeling. We have open-sourced \textbf{SocioBench} at \url{https://github.com/JiaWANG-TJ/SocioBench}."
}