@inproceedings{gardiner-etal-2024-data,
title = "Data Anonymization for Privacy-Preserving Large Language Model Fine-Tuning on Call Transcripts",
author = "Gardiner, Shayna and
Habib, Tania and
Humphreys, Kevin and
Azizi, Masha and
Mailhot, Frederic and
Paling, Anne and
Thomas, Preston and
Zhang, Nathan",
editor = {Volodina, Elena and
Alfter, David and
Dobnik, Simon and
Lindstr{\"o}m Tiedemann, Therese and
Mu{\~n}oz S{\'a}nchez, Ricardo and
Szawerna, Maria Irena and
Vu, Xuan-Son},
booktitle = "Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.caldpseudo-1.8/",
pages = "64--75",
abstract = "Large language models in public-facing industrial applications must accurately process data for the domain in which they are deployed, but they must not leak sensitive or confidential information when used. We present a process for anonymizing training data, a framework for quantitatively and qualitatively assessing the effectiveness of this process, and an assessment of the effectiveness of models fine-tuned on anonymized data in comparison with commercially available LLM APIs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gardiner-etal-2024-data">
<titleInfo>
<title>Data Anonymization for Privacy-Preserving Large Language Model Fine-Tuning on Call Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shayna</namePart>
<namePart type="family">Gardiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Habib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Humphreys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masha</namePart>
<namePart type="family">Azizi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Mailhot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Paling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preston</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models in public-facing industrial applications must accurately process data for the domain in which they are deployed, but they must not leak sensitive or confidential information when used. We present a process for anonymizing training data, a framework for quantitatively and qualitatively assessing the effectiveness of this process, and an assessment of the effectiveness of models fine-tuned on anonymized data in comparison with commercially available LLM APIs.</abstract>
<identifier type="citekey">gardiner-etal-2024-data</identifier>
<location>
<url>https://aclanthology.org/2024.caldpseudo-1.8/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>64</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Anonymization for Privacy-Preserving Large Language Model Fine-Tuning on Call Transcripts
%A Gardiner, Shayna
%A Habib, Tania
%A Humphreys, Kevin
%A Azizi, Masha
%A Mailhot, Frederic
%A Paling, Anne
%A Thomas, Preston
%A Zhang, Nathan
%Y Volodina, Elena
%Y Alfter, David
%Y Dobnik, Simon
%Y Lindström Tiedemann, Therese
%Y Muñoz Sánchez, Ricardo
%Y Szawerna, Maria Irena
%Y Vu, Xuan-Son
%S Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F gardiner-etal-2024-data
%X Large language models in public-facing industrial applications must accurately process data for the domain in which they are deployed, but they must not leak sensitive or confidential information when used. We present a process for anonymizing training data, a framework for quantitatively and qualitatively assessing the effectiveness of this process, and an assessment of the effectiveness of models fine-tuned on anonymized data in comparison with commercially available LLM APIs.
%U https://aclanthology.org/2024.caldpseudo-1.8/
%P 64-75
Markdown (Informal)
[Data Anonymization for Privacy-Preserving Large Language Model Fine-Tuning on Call Transcripts](https://aclanthology.org/2024.caldpseudo-1.8/) (Gardiner et al., CALD-pseudo 2024)
ACL
- Shayna Gardiner, Tania Habib, Kevin Humphreys, Masha Azizi, Frederic Mailhot, Anne Paling, Preston Thomas, and Nathan Zhang. 2024. Data Anonymization for Privacy-Preserving Large Language Model Fine-Tuning on Call Transcripts. In Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024), pages 64–75, St. Julian’s, Malta. Association for Computational Linguistics.