<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="makinde-etal-2026-psychmet">
    <titleInfo>
        <title>Psychmet- Measurement Foundational Competencies ChatBot</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Henry</namePart>
        <namePart type="family">Makinde</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hope</namePart>
        <namePart type="family">Adegoke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mubarak</namePart>
        <namePart type="family">Mojoyinola</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): Full Papers</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">979-8-9983004-0-0</identifier>
    </relatedItem>
    <abstract>PsychMet is a domain-grounded chatbot that uses a GPT-4.1 conversational model with retrieval-augmented generation over a curated psychometrics corpus, with emphasis on IRT and NCME competencies. Using the RAGAS framework on a 30-question set, PsychMet achieved an Overall score of 0.539, with strengths in Answer Correctness (0.810) and Context Recall (0.671), moderate Faithfulness (0.588), and weaknesses in Answer Relevancy (0.284), Context Precision (0.425), and Context Relevancy (0.474). This pattern suggests that retrieval breadth is outpacing specificity. We outline targeted fixes — such as hybrid sparse+dense retrieval with light filtering and question-first prompting — to tighten focus without sacrificing coverage. PsychMet is accurate and transparently sourced for exploratory learning; with retrieval tightening and answer scoping, it can better support time-bound professional workflows.</abstract>
    <identifier type="citekey">makinde-etal-2026-psychmet</identifier>
    <location>
        <url>https://aclanthology.org/2026.aimecon-main.2/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>7</start>
            <end>12</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Psychmet- Measurement Foundational Competencies ChatBot
%A Makinde, Henry
%A Adegoke, Hope
%A Mojoyinola, Mubarak
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-0-0
%F makinde-etal-2026-psychmet
%X PsychMet is a domain-grounded chatbot that uses a GPT-4.1 conversational model with retrieval-augmented generation over a curated psychometrics corpus, with emphasis on IRT and NCME competencies. Using the RAGAS framework on a 30-question set, PsychMet achieved an Overall score of 0.539, with strengths in Answer Correctness (0.810) and Context Recall (0.671), moderate Faithfulness (0.588), and weaknesses in Answer Relevancy (0.284), Context Precision (0.425), and Context Relevancy (0.474). This pattern suggests that retrieval breadth is outpacing specificity. We outline targeted fixes — such as hybrid sparse+dense retrieval with light filtering and question-first prompting — to tighten focus without sacrificing coverage. PsychMet is accurate and transparently sourced for exploratory learning; with retrieval tightening and answer scoping, it can better support time-bound professional workflows.
%U https://aclanthology.org/2026.aimecon-main.2/
%P 7-12

Markdown (Informal)

[Psychmet- Measurement Foundational Competencies ChatBot](https://aclanthology.org/2026.aimecon-main.2/) (Makinde et al., AIME-Con 2026)

• Psychmet- Measurement Foundational Competencies ChatBot (Makinde et al., AIME-Con 2026)

ACL

• Henry Makinde, Hope Adegoke, and Mubarak Mojoyinola. 2026. Psychmet- Measurement Foundational Competencies ChatBot. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 7–12, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).