@inproceedings{kulkarni-etal-2025-guir,
    title = "{GUIR} at {S}em{E}val-2025 Task 4: Adaptive Weight Tuning with Gradual Negative Matching for {LLM} Unlearning",
    author = "Kulkarni, Hrishikesh  and
      Goharian, Nazli  and
      Frieder, Ophir",
    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/transition-to-people-yaml/2025.semeval-1.152/",
    pages = "1152--1158",
    ISBN = "979-8-89176-273-2",
    abstract = "Machine Unlearning for Large Language Models, referred to as LLM Unlearning is getting more and more attention as a result of regurgitation of sensitive and harmful content. In this paper, we present our method architecture, results, and analysis of our submission to Task4: Unlearning sensitive content from Large Language Models. This task includes three subtasks of LLM Unlearning on 1) Long Synthetic documents, 2) Short Synthetic documents, and 3) Real Training documents. Getting rid of the impact of undesirable and unauthorized responses is the core objective of unlearning. Furthermore, it is expected that unlearning should not have an adverse impact on the usability of the model. In this paper, we provide an approach for LLM unlearning that tries to make the model forget while maintaining usability of the model. We perform adaptive weight tuning with Gradient Ascent, KL minimization and Gradual Negative Matching loss functions. Our submission balances retain and forget abilities of the model while outperforming provided benchmarks."
}