@inproceedings{sabzevari-etal-2025-nlpart,
    title = "{NLPART} at {S}em{E}val-2025 Task 4: Forgetting is harder than Learning",
    author = "Sabzevari, Hoorieh  and
      Molazadeh Oskuee, Milad  and
      Abedini, Tohid  and
      Zamaninejad, Ghazal  and
      Baruni, Sara  and
      Amirmahani, Zahra  and
      Salehoof, Amirmohammad",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.304/",
    pages = "2336--2341",
    ISBN = "979-8-89176-273-2",
    abstract = "Unlearning is a critical capability for ensuring privacy, security, and compliance in AI systems, enabling models to forget specific data while retaining overall performance. In this work, we participated in Task 4 of SemEval 2025, which focused on unlearning across three sub-tasks: (1) long-form synthetic creative documents, (2) short-form synthetic biographies containing personally identifiable information, and (3) real documents sampled from the target model{'}s training dataset. We conducted four experiments, employing Supervised Fine-Tuning (SFT) and Negative Preference Optimization (NPO). Despite achieving good performance on the retain set{---}data that the model was supposed to remember{---}our findings demonstrate that these techniques did not perform well on the forget set, where unlearning was required."
}