@inproceedings{kurt-afli-2026-operationalising,
    title = "Operationalising the ``Right to Be Forgotten'' in {LLM}s: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments",
    author = "Kurt, Esen  and
      Afli, Haithem",
    editor = "Afli, Haithem  and
      Bouamor, Houda  and
      Zaghouani, Wajdi  and
      Ghannay, Sahar  and
      Hossain, Shehenaz",
    booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences ({P}olitical{NLP} 2026)",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/paragraph-normalization/2026.politicalnlp-1.9/",
    doi = "10.63317/5erg5f5fh3k9",
    pages = "77--86",
    abstract = "Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential content raises regulatory concerns under frameworks such as the GDPR and its ``right to be forgotten''. Translating such legal principles into large-scale generative systems presents significant technical challenges. We introduce a lightweight sequential unlearning framework that explicitly separates retention and suppression objectives. The method first stabilises benign capabilities through positive fine-tuning, then applies layer-restricted negative fine-tuning to suppress designated sensitive patterns while preserving general language competence. Experiments on the SemEval-2025 LLM Unlearning benchmark demonstrate effective behavioural suppression with minimal impact on factual accuracy and fluency. GPT-2 exhibits greater robustness than DistilGPT-2, highlighting the role of model capacity in privacy-aligned adaptation. We position sequential unlearning as a practical and reproducible mechanism for operationalising data erasure requirements in politically deployed LLMs."
}