@inproceedings{borisiuk-etal-2026-anatomy,
    title = "Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning",
    author = "Borisiuk, Anna  and
      Savchenko, Andrey  and
      Panchenko, Alexander  and
      Tutubalina, Elena",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1287/",
    pages = "25846--25859",
    ISBN = "979-8-89176-395-1",
    abstract = "Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from pretraining or supervised fine-tuning (SFT). In this paper, we introduce DUAL (Dual Unlearning Evaluation across Training Stages), a benchmark of 28.6k Wikidata-derived triplets annotated with fact popularity using Wikipedia link counts and LLM-based salience scores. Our experiments show that pretrained and SFT models respond differently to unlearning. An SFT step on the forget data yields smoother forgetting, more stable tuning, and 10{--}50{\%} higher retention, while direct unlearning on pretrained models remains unstable and prone to relearning or catastrophic forgetting."
}