Operationalising the "Right to Be Forgotten" in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments

Esen Kurt, Haithem Afli


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.
Anthology ID:
2026.politicalnlp-1.9
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Haithem Afli, Houda Bouamor, Wajdi Zaghouani, Sahar Ghannay, Shehenaz Hossain
Venues:
PoliticalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
77–86
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-politicalnlp-09
DOI:
10.63317/5erg5f5fh3k9
Bibkey:
Cite (ACL):
Esen Kurt and Haithem Afli. 2026. Operationalising the "Right to Be Forgotten" in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments. In Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026), pages 77–86, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Operationalising the “Right to Be Forgotten” in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments (Kurt & Afli, PoliticalNLP 2026)
Copy Citation: