@inproceedings{arnold-etal-2023-disentangling,
    title = "Disentangling the Linguistic Competence of Privacy-Preserving {BERT}",
    author = "Arnold, Stefan  and
      Kemmerzell, Nils  and
      Schreiner, Annika",
    editor = "Belinkov, Yonatan  and
      Hao, Sophie  and
      Jumelet, Jaap  and
      Kim, Najoung  and
      McCarthy, Arya  and
      Mohebbi, Hosein",
    booktitle = "Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2023.blackboxnlp-1.5/",
    doi = "10.18653/v1/2023.blackboxnlp-1.5",
    pages = "65--75",
    abstract = "Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on perturbed text. Employing a series of interpretation techniques on the internal representations extracted from BERT trained on perturbed pre-text, we intend to disentangle at the linguistic level the distortion induced by differential privacy. Experimental results from a representational similarity analysis indicate that the overall similarity of internal representations is substantially reduced. Using probing tasks to unpack this dissimilarity, we find evidence that text-to-text privatization affects the linguistic competence across several formalisms, encoding localized properties of words while falling short at encoding the contextual relationships between spans of words."
}