@inproceedings{orlikowski-etal-2025-beyond,
    title = "Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions",
    author = {Orlikowski, Matthias  and
      Pei, Jiaxin  and
      R{\"o}ttger, Paul  and
      Cimiano, Philipp  and
      Jurgens, David  and
      Hovy, Dirk},
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.104/",
    pages = "2092--2111",
    ISBN = "979-8-89176-251-0",
    abstract = "People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person{'}s sociodemographic characteristics. LLMs have also been used to label data, but recent work has shown that models perform poorly when prompted with sociodemographic attributes, suggesting limited inherent sociodemographic knowledge. Here, we ask whether LLMs can be trained to be accurate sociodemographic models of annotator variation. Using a curated dataset of five tasks with standardized sociodemographics, we show that models do improve in sociodemographic prompting when trained but that this performance gain is largely due to models learning annotator-specific behaviour rather than sociodemographic behaviours. Across all tasks, our results suggest that models learn little meaningful connection between sociodemographics and annotation, raising doubts about the current use of LLMs for simulating sociodemographic variation and behaviour."
}