<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borisiuk-etal-2026-silence">
    <titleInfo>
        <title>The Silence of the Facts: Popularity as a Barrier to Machine Unlearning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Borisiuk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrey</namePart>
        <namePart type="family">Savchenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Panchenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elena</namePart>
        <namePart type="family">Tutubalina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="given">Diego</namePart>
            <namePart type="family">Rodriguez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ona</namePart>
            <namePart type="family">de Gibert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-393-7</identifier>
    </relatedItem>
    <abstract>Machine Unlearning is a valuable ability of LLMs, enabling the removal of unsafe, outdated, or private information. Existing unlearning methods, however, are often evaluated under the assumption that all facts are equally challenging to forget. Controllable knowledge removal is essential for reliable NLP systems. In this paper, we investigate whether fact popularity influences the efficiency of LLM unlearning. To answer this question, we build **UNLamb** benchmark designed to systematically investigate this relationship. It consists of 11.6k question-answer pairs derived from real-world knowledge in Wikidata, explicitly partitioned into rare and popular facts. Using this benchmark, we perform a comprehensive evaluation of state-of-the-art unlearning algorithms on a set of models of different sizes. We conduct a comprehensive analysis of four unlearning methods across three validation sets and two LLMs. We show that larger models struggle more to forget popular entities, often damaging related knowledge in the process. In contrast, it is much easier to remove rare facts without side effects.</abstract>
    <identifier type="citekey">borisiuk-etal-2026-silence</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-srw.46/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>515</start>
            <end>526</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Silence of the Facts: Popularity as a Barrier to Machine Unlearning
%A Borisiuk, Anna
%A Savchenko, Andrey
%A Panchenko, Alexander
%A Tutubalina, Elena
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F borisiuk-etal-2026-silence
%X Machine Unlearning is a valuable ability of LLMs, enabling the removal of unsafe, outdated, or private information. Existing unlearning methods, however, are often evaluated under the assumption that all facts are equally challenging to forget. Controllable knowledge removal is essential for reliable NLP systems. In this paper, we investigate whether fact popularity influences the efficiency of LLM unlearning. To answer this question, we build **UNLamb** benchmark designed to systematically investigate this relationship. It consists of 11.6k question-answer pairs derived from real-world knowledge in Wikidata, explicitly partitioned into rare and popular facts. Using this benchmark, we perform a comprehensive evaluation of state-of-the-art unlearning algorithms on a set of models of different sizes. We conduct a comprehensive analysis of four unlearning methods across three validation sets and two LLMs. We show that larger models struggle more to forget popular entities, often damaging related knowledge in the process. In contrast, it is much easier to remove rare facts without side effects.
%U https://aclanthology.org/2026.acl-srw.46/
%P 515-526

Markdown (Informal)

[The Silence of the Facts: Popularity as a Barrier to Machine Unlearning](https://aclanthology.org/2026.acl-srw.46/) (Borisiuk et al., ACL 2026)

• The Silence of the Facts: Popularity as a Barrier to Machine Unlearning (Borisiuk et al., ACL 2026)

ACL

• Anna Borisiuk, Andrey Savchenko, Alexander Panchenko, and Elena Tutubalina. 2026. The Silence of the Facts: Popularity as a Barrier to Machine Unlearning. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 515–526, San Diego, California, United States. Association for Computational Linguistics.