<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-yang-2023-unlearn">
    <titleInfo>
        <title>Unlearn What You Want to Forget: Efficient Unlearning for LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiaao</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Diyi</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <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">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy issues and violations of data protection regulations. As a result, the ability to easily remove data related to individual users from such models while not deteriorating their predictive quality after the removal becomes increasingly important. To address these issues, in this work, we propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals, by introducing lightweight unlearning layers learned with a selective teacher-student objective into the transformers. In addition, we introduce a fusion mechanism to effectively combine different unlearning layers that learns to forget different sets of data to handle a sequence of forgetting operations. Experiments on classification and generation tasks demonstrate the effectiveness of our proposed methods compared to the state-of-the-art baselines.</abstract>
    <identifier type="citekey">chen-yang-2023-unlearn</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.738</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.738/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>12041</start>
            <end>12052</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unlearn What You Want to Forget: Efficient Unlearning for LLMs
%A Chen, Jiaao
%A Yang, Diyi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chen-yang-2023-unlearn
%X Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy issues and violations of data protection regulations. As a result, the ability to easily remove data related to individual users from such models while not deteriorating their predictive quality after the removal becomes increasingly important. To address these issues, in this work, we propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals, by introducing lightweight unlearning layers learned with a selective teacher-student objective into the transformers. In addition, we introduce a fusion mechanism to effectively combine different unlearning layers that learns to forget different sets of data to handle a sequence of forgetting operations. Experiments on classification and generation tasks demonstrate the effectiveness of our proposed methods compared to the state-of-the-art baselines.
%R 10.18653/v1/2023.emnlp-main.738
%U https://aclanthology.org/2023.emnlp-main.738/
%U https://doi.org/10.18653/v1/2023.emnlp-main.738
%P 12041-12052

Markdown (Informal)

[Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://aclanthology.org/2023.emnlp-main.738/) (Chen & Yang, EMNLP 2023)

• Unlearn What You Want to Forget: Efficient Unlearning for LLMs (Chen & Yang, EMNLP 2023)

ACL

• Jiaao Chen and Diyi Yang. 2023. Unlearn What You Want to Forget: Efficient Unlearning for LLMs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12041–12052, Singapore. Association for Computational Linguistics.