@inproceedings{loiseau-etal-2025-tau,
    title = "Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization",
    author = "Loiseau, Gabriel  and
      Sileo, Damien  and
      Riquet, Damien  and
      Meyer, Maxime  and
      Tommasi, Marc",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-zheyuan-zhang-jhu/2025.emnlp-demos.16/",
    doi = "10.18653/v1/2025.emnlp-demos.16",
    pages = "216--227",
    ISBN = "979-8-89176-334-0",
    abstract = "Text anonymization is the process of removing or obfuscating information from textual data to protect the privacy of individuals. This process inherently involves a complex trade-off between privacy protection and information preservation, where stringent anonymization methods can significantly impact the text{'}s utility for downstream applications. Evaluating the effectiveness of text anonymization proves challenging from both privacy and utility perspectives, as there is no universal benchmark that can comprehensively assess anonymization techniques across diverse, and sometimes contradictory contexts. We present Tau-Eval, an open-source framework for benchmarking text anonymization methods through the lens of privacy and utility task sensitivity. A Python library, code, documentation and tutorials are publicly available."
}