<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-relabeling">
    <titleInfo>
        <title>Relabeling Minimal Training Subset to Flip a Prediction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinghan</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Linjie</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lequan</namePart>
        <namePart type="family">Yu</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>Findings of the Association for Computational Linguistics: EACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</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>When facing an unsatisfactory prediction from a machine learning model, users can be interested in investigating the underlying reasons and exploring the potential for reversing the outcome. We ask: To flip the prediction on a test point x_t, how to identify the smallest training subset \mathcalS_t that we need to relabel?We propose an efficient algorithm to identify and relabel such a subset via an extended influence function for binary classification models with convex loss.We find that relabeling fewer than 2% of the training points can always flip a prediction.This mechanism can serve multiple purposes: (1) providing an approach to challenge a model prediction by altering training points; (2) evaluating model robustness with the cardinality of the subset (i.e., |\mathcalS_t|); we show that |\mathcalS_t| is highly related to the noise ratio in the training set and |\mathcalS_t| is correlated with but complementary to predicted probabilities; and (3) revealing training points lead to group attribution bias. To the best of our knowledge, we are the first to investigate identifying and relabeling the minimal training subset required to flip a given prediction.</abstract>
    <identifier type="citekey">yang-etal-2024-relabeling</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-eacl.73</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1085</start>
            <end>1098</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Relabeling Minimal Training Subset to Flip a Prediction
%A Yang, Jinghan
%A Xu, Linjie
%A Yu, Lequan
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F yang-etal-2024-relabeling
%X When facing an unsatisfactory prediction from a machine learning model, users can be interested in investigating the underlying reasons and exploring the potential for reversing the outcome. We ask: To flip the prediction on a test point x_t, how to identify the smallest training subset \mathcalS_t that we need to relabel?We propose an efficient algorithm to identify and relabel such a subset via an extended influence function for binary classification models with convex loss.We find that relabeling fewer than 2% of the training points can always flip a prediction.This mechanism can serve multiple purposes: (1) providing an approach to challenge a model prediction by altering training points; (2) evaluating model robustness with the cardinality of the subset (i.e., |\mathcalS_t|); we show that |\mathcalS_t| is highly related to the noise ratio in the training set and |\mathcalS_t| is correlated with but complementary to predicted probabilities; and (3) revealing training points lead to group attribution bias. To the best of our knowledge, we are the first to investigate identifying and relabeling the minimal training subset required to flip a given prediction.
%U https://aclanthology.org/2024.findings-eacl.73
%P 1085-1098

Markdown (Informal)

[Relabeling Minimal Training Subset to Flip a Prediction](https://aclanthology.org/2024.findings-eacl.73) (Yang et al., Findings 2024)

• Relabeling Minimal Training Subset to Flip a Prediction (Yang et al., Findings 2024)

ACL

• Jinghan Yang, Linjie Xu, and Lequan Yu. 2024. Relabeling Minimal Training Subset to Flip a Prediction. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1085–1098, St. Julian’s, Malta. Association for Computational Linguistics.