<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="majumder-etal-2023-interfair">
    <titleInfo>
        <title>InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bodhisattwa</namePart>
        <namePart type="family">Majumder</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zexue</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julian</namePart>
        <namePart type="family">McAuley</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>Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information ‘fairly,’ with explanations, rather than blindly eliminating it. This fair balance is often subjective and can be challenging to achieve algorithmically. We explore two interactive setups with a frozen predictive model and show that users able to provide feedback can achieve a better and fairer balance between task performance and bias mitigation. In one setup, users, by interacting with test examples, further decreased bias in the explanations (5-8%) while maintaining the same prediction accuracy. In the other setup, human feedback was able to disentangle associated bias and predictive information from the input leading to superior bias mitigation and improved task performance (4-5%) simultaneously.</abstract>
    <identifier type="citekey">majumder-etal-2023-interfair</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.589</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.589</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>9466</start>
            <end>9471</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
%A Majumder, Bodhisattwa
%A He, Zexue
%A McAuley, Julian
%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 majumder-etal-2023-interfair
%X Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information ‘fairly,’ with explanations, rather than blindly eliminating it. This fair balance is often subjective and can be challenging to achieve algorithmically. We explore two interactive setups with a frozen predictive model and show that users able to provide feedback can achieve a better and fairer balance between task performance and bias mitigation. In one setup, users, by interacting with test examples, further decreased bias in the explanations (5-8%) while maintaining the same prediction accuracy. In the other setup, human feedback was able to disentangle associated bias and predictive information from the input leading to superior bias mitigation and improved task performance (4-5%) simultaneously.
%R 10.18653/v1/2023.emnlp-main.589
%U https://aclanthology.org/2023.emnlp-main.589
%U https://doi.org/10.18653/v1/2023.emnlp-main.589
%P 9466-9471

Markdown (Informal)

[InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions](https://aclanthology.org/2023.emnlp-main.589) (Majumder et al., EMNLP 2023)

• InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions (Majumder et al., EMNLP 2023)

ACL

• Bodhisattwa Majumder, Zexue He, and Julian McAuley. 2023. InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9466–9471, Singapore. Association for Computational Linguistics.