<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nghiem-etal-2025-rich">
    <titleInfo>
        <title>‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Huy</namePart>
        <namePart type="family">Nghiem</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Phuong-Anh</namePart>
        <namePart type="family">Nguyen-Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Prindle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rachel</namePart>
        <namePart type="family">Rudinger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hal</namePart>
        <namePart type="given">Daumé</namePart>
        <namePart type="family">Iii</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially-sensitive decisions still remain underexplored. We present a large-scale audit of LLMs’ treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science. Leveraging a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2). Results from 5 million prompts reveals that LLMs consistently favor low-SES applicants—even when controlling for academic performance—and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers. We then propose DPAF, a dual-process audit framework to probe LLMs’ reasoning behaviors in sensitive applications.</abstract>
    <identifier type="citekey">nghiem-etal-2025-rich</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.1064/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>21033</start>
            <end>21067</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?
%A Nghiem, Huy
%A Nguyen-Le, Phuong-Anh
%A Prindle, John
%A Rudinger, Rachel
%A Iii, Hal Daumé
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F nghiem-etal-2025-rich
%X Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially-sensitive decisions still remain underexplored. We present a large-scale audit of LLMs’ treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science. Leveraging a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2). Results from 5 million prompts reveals that LLMs consistently favor low-SES applicants—even when controlling for academic performance—and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers. We then propose DPAF, a dual-process audit framework to probe LLMs’ reasoning behaviors in sensitive applications.
%U https://aclanthology.org/2025.emnlp-main.1064/
%P 21033-21067

Markdown (Informal)

[‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?](https://aclanthology.org/2025.emnlp-main.1064/) (Nghiem et al., EMNLP 2025)

• ‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ? (Nghiem et al., EMNLP 2025)

ACL

• Huy Nghiem, Phuong-Anh Nguyen-Le, John Prindle, Rachel Rudinger, and Hal Daumé Iii. 2025. ‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 21033–21067, Suzhou, China. Association for Computational Linguistics.