@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurt-afli-2026-operationalising">
<titleInfo>
<title>Operationalising the “Right to Be Forgotten” in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esen</namePart>
<namePart type="family">Kurt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shehenaz</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">kurt-afli-2026-operationalising</identifier>
<identifier type="doi">10.63317/5erg5f5fh3k9</identifier>
<location>
<url>https://aclanthology.org/2026.politicalnlp-1.9/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>77</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Operationalising the “Right to Be Forgotten” in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments
%A Kurt, Esen
%A Afli, Haithem
%Y Afli, Haithem
%Y Bouamor, Houda
%Y Zaghouani, Wajdi
%Y Ghannay, Sahar
%Y Hossain, Shehenaz
%S Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F kurt-afli-2026-operationalising
%X 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.
%R 10.63317/5erg5f5fh3k9
%U https://aclanthology.org/2026.politicalnlp-1.9/
%U https://doi.org/10.63317/5erg5f5fh3k9
%P 77-86
Markdown (Informal)
[Operationalising the "Right to Be Forgotten" in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments](https://aclanthology.org/2026.politicalnlp-1.9/) (Kurt & Afli, PoliticalNLP 2026)
ACL