<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nwatu-etal-2025-uplifting">
    <titleInfo>
        <title>Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Joan</namePart>
        <namePart type="family">Nwatu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Oana</namePart>
        <namePart type="family">Ignat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rada</namePart>
        <namePart type="family">Mihalcea</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-189-6</identifier>
    </relatedItem>
    <abstract>Recent work has demonstrated that the unequal representation of cultures and socioeconomic groups in training data leads to biased Large Multi-modal (LMM) models. To improve LMM model performance on underrepresented data, we propose and evaluate several prompting strategies using non-English, geographic, and socioeconomic attributes. We show that these geographic and socioeconomic integrated prompts favor retrieving topic appearances commonly found in data from low-income households across different countries leading to improved LMM model performance on lower-income data. Our analyses identify and highlight contexts where these strategies yield the most improvements.</abstract>
    <identifier type="citekey">nwatu-etal-2025-uplifting</identifier>
    <identifier type="doi">10.18653/v1/2025.naacl-long.106</identifier>
    <location>
        <url>https://aclanthology.org/2025.naacl-long.106/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>2127</start>
            <end>2144</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models
%A Nwatu, Joan
%A Ignat, Oana
%A Mihalcea, Rada
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F nwatu-etal-2025-uplifting
%X Recent work has demonstrated that the unequal representation of cultures and socioeconomic groups in training data leads to biased Large Multi-modal (LMM) models. To improve LMM model performance on underrepresented data, we propose and evaluate several prompting strategies using non-English, geographic, and socioeconomic attributes. We show that these geographic and socioeconomic integrated prompts favor retrieving topic appearances commonly found in data from low-income households across different countries leading to improved LMM model performance on lower-income data. Our analyses identify and highlight contexts where these strategies yield the most improvements.
%R 10.18653/v1/2025.naacl-long.106
%U https://aclanthology.org/2025.naacl-long.106/
%U https://doi.org/10.18653/v1/2025.naacl-long.106
%P 2127-2144

Markdown (Informal)

[Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models](https://aclanthology.org/2025.naacl-long.106/) (Nwatu et al., NAACL 2025)

• Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models (Nwatu et al., NAACL 2025)

ACL

• Joan Nwatu, Oana Ignat, and Rada Mihalcea. 2025. Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2127–2144, Albuquerque, New Mexico. Association for Computational Linguistics.