<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chrzan-domingue-2026-consensus">
    <titleInfo>
        <title>Consensus without Accuracy: Investigating LLM’s Recovery of Item Difficulty Using Paired Comparisons</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="given">Leon</namePart>
        <namePart type="family">Chrzan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Domingue</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Joshua</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Ormerod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Magdalen</namePart>
            <namePart type="family">Beiting-Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>National Council on Measurement in Education (NCME)</publisher>
            <place>
                <placeTerm type="text">Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-9983004-1-7</identifier>
    </relatedItem>
    <abstract>This study evaluates whether large language models (LLMs) can recover item difficulty estimates through Bradley-Terry modeling from pairwise comparisons of items. Across five Item Response Warehouse datasets and four LLMs, we examine alignment between LLM pairwise-derived difficulty rankings and 1PL IRT parameters, with implications for scalable, AI-assisted item calibration.</abstract>
    <identifier type="citekey">chrzan-domingue-2026-consensus</identifier>
    <location>
        <url>https://aclanthology.org/2026.aimecon-wip.4/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>24</start>
            <end>36</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Consensus without Accuracy: Investigating LLM’s Recovery of Item Difficulty Using Paired Comparisons
%A Chrzan, Michael Leon
%A Domingue, Benjamin
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-1-7
%F chrzan-domingue-2026-consensus
%X This study evaluates whether large language models (LLMs) can recover item difficulty estimates through Bradley-Terry modeling from pairwise comparisons of items. Across five Item Response Warehouse datasets and four LLMs, we examine alignment between LLM pairwise-derived difficulty rankings and 1PL IRT parameters, with implications for scalable, AI-assisted item calibration.
%U https://aclanthology.org/2026.aimecon-wip.4/
%P 24-36

Markdown (Informal)

[Consensus without Accuracy: Investigating LLM’s Recovery of Item Difficulty Using Paired Comparisons](https://aclanthology.org/2026.aimecon-wip.4/) (Chrzan & Domingue, AIME-Con 2026)

• Consensus without Accuracy: Investigating LLM’s Recovery of Item Difficulty Using Paired Comparisons (Chrzan & Domingue, AIME-Con 2026)

ACL

• Michael Leon Chrzan and Benjamin Domingue. 2026. Consensus without Accuracy: Investigating LLM’s Recovery of Item Difficulty Using Paired Comparisons. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 24–36, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).