@inproceedings{benli-etal-2026-tune,
title = "{TUNE}: A Task For {T}urkish Machine Unlearning For Data Privacy",
author = {Benli, Doruk and
Cano{\u{g}}lu, Ada and
G{\"o}nen{\c{c}}er, Nehir {\.I}lkim and
Kek{\"u}ll{\"u}o{\u{g}}lu, Dilara},
editor = {Oflazer, Kemal and
K{\"o}ksal, Abdullatif and
Varol, Onur},
booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigturk-1.3/",
pages = "28--37",
ISBN = "979-8-89176-370-8",
abstract = "Most large language models (LLMs) are trainedon massive datasets that include private infor-mation, which may be disclosed to third-partyusers in output generation. Developers put de-fences to prevent the generation of harmful andprivate information, but jailbreaking methodscan be used to bypass them. Machine unlearn-ing aims to remove information that may beprivate or harmful from the model{'}s genera-tion without retraining the model from scratch.While machine unlearning has gained somepopularity to counter the removal of privateinformation, especially in English, little to noattention has been given to Turkish unlearn-ing paradigms or existing benchmarks. In thisstudy, we introduce TUNE (Turkish Unlearn-ing Evaluation), the first benchmark datasetfor Turkish unlearning task for personal infor-mation. TUNE consists of 9842 input-targettext pairs about 50 fictitious personalities withtwo training task types: (1) Q A and (2) In-formation Request. We fine-tuned the mT5base model to evaluate various unlearning meth-ods, including our proposed approach. We findthat while current methods can help unlearnunwanted private information in Turkish, theyalso unlearn other information we want to re-tain in the model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benli-etal-2026-tune">
<titleInfo>
<title>TUNE: A Task For Turkish Machine Unlearning For Data Privacy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Doruk</namePart>
<namePart type="family">Benli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ada</namePart>
<namePart type="family">Canoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nehir</namePart>
<namePart type="given">İlkim</namePart>
<namePart type="family">Gönençer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilara</namePart>
<namePart type="family">Keküllüoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Oflazer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullatif</namePart>
<namePart type="family">Köksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Varol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-370-8</identifier>
</relatedItem>
<abstract>Most large language models (LLMs) are trainedon massive datasets that include private infor-mation, which may be disclosed to third-partyusers in output generation. Developers put de-fences to prevent the generation of harmful andprivate information, but jailbreaking methodscan be used to bypass them. Machine unlearn-ing aims to remove information that may beprivate or harmful from the model’s genera-tion without retraining the model from scratch.While machine unlearning has gained somepopularity to counter the removal of privateinformation, especially in English, little to noattention has been given to Turkish unlearn-ing paradigms or existing benchmarks. In thisstudy, we introduce TUNE (Turkish Unlearn-ing Evaluation), the first benchmark datasetfor Turkish unlearning task for personal infor-mation. TUNE consists of 9842 input-targettext pairs about 50 fictitious personalities withtwo training task types: (1) Q A and (2) In-formation Request. We fine-tuned the mT5base model to evaluate various unlearning meth-ods, including our proposed approach. We findthat while current methods can help unlearnunwanted private information in Turkish, theyalso unlearn other information we want to re-tain in the model.</abstract>
<identifier type="citekey">benli-etal-2026-tune</identifier>
<location>
<url>https://aclanthology.org/2026.sigturk-1.3/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>28</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TUNE: A Task For Turkish Machine Unlearning For Data Privacy
%A Benli, Doruk
%A Canoğlu, Ada
%A Gönençer, Nehir İlkim
%A Keküllüoğlu, Dilara
%Y Oflazer, Kemal
%Y Köksal, Abdullatif
%Y Varol, Onur
%S Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-370-8
%F benli-etal-2026-tune
%X Most large language models (LLMs) are trainedon massive datasets that include private infor-mation, which may be disclosed to third-partyusers in output generation. Developers put de-fences to prevent the generation of harmful andprivate information, but jailbreaking methodscan be used to bypass them. Machine unlearn-ing aims to remove information that may beprivate or harmful from the model’s genera-tion without retraining the model from scratch.While machine unlearning has gained somepopularity to counter the removal of privateinformation, especially in English, little to noattention has been given to Turkish unlearn-ing paradigms or existing benchmarks. In thisstudy, we introduce TUNE (Turkish Unlearn-ing Evaluation), the first benchmark datasetfor Turkish unlearning task for personal infor-mation. TUNE consists of 9842 input-targettext pairs about 50 fictitious personalities withtwo training task types: (1) Q A and (2) In-formation Request. We fine-tuned the mT5base model to evaluate various unlearning meth-ods, including our proposed approach. We findthat while current methods can help unlearnunwanted private information in Turkish, theyalso unlearn other information we want to re-tain in the model.
%U https://aclanthology.org/2026.sigturk-1.3/
%P 28-37
Markdown (Informal)
[TUNE: A Task For Turkish Machine Unlearning For Data Privacy](https://aclanthology.org/2026.sigturk-1.3/) (Benli et al., SIGTURK 2026)
ACL
- Doruk Benli, Ada Canoğlu, Nehir İlkim Gönençer, and Dilara Keküllüoğlu. 2026. TUNE: A Task For Turkish Machine Unlearning For Data Privacy. In Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026), pages 28–37, Rabat, Morocco. Association for Computational Linguistics.