@inproceedings{dobrzeniecka-etal-2025-improving,
    title = "Improving Causal Interventions in Amnesic Probing with Mean Projection or {LEACE}",
    author = "Dobrzeniecka, Alicja  and
      Fokkens, Antske  and
      Sommerauer, Pia",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.findings-acl.674/",
    doi = "10.18653/v1/2025.findings-acl.674",
    pages = "12981--12993",
    ISBN = "979-8-89176-256-5",
    abstract = "Amnesic probing is a technique used to examine the influence of specific linguistic information on the behaviour of a model. This involves identifying and removing the relevant information and then assessing whether the model{'}s performance on the main task changes. If the removed information is relevant, the model{'}s performance should decline. The difficulty with this approach lies in removing \textit{only} the target information while leaving other information unchanged. It has been shown that Iterative Nullspace Projection (INLP), a widely used removal technique, introduces random modifications to representations when eliminating target information. We demonstrate that Mean Projection (MP) and LEACE, two proposed alternatives, remove information in a more targeted manner, thereby enhancing the potential for obtaining behavioural explanations through Amnesic Probing."
}