<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barber-etal-2026-multi">
    <titleInfo>
        <title>Multi-Agent LLM Annotation and Scoring for Training Fine-Grained K-12 Writing-Feedback Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="given">O</namePart>
        <namePart type="family">Barber</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="given">P</namePart>
        <namePart type="family">Hemenway</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martha</namePart>
        <namePart type="family">Bellows</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Susan</namePart>
        <namePart type="family">Lottridge</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): Coordinated Session 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">979-8-9983004-2-4</identifier>
    </relatedItem>
    <abstract>Fine-grained formative writing feedback needs dense, standards-aligned labels that human annotation cannot supply at scale. We describe a multi-agent LLM pipeline producing verified silver labels, and then train small deterministic transformer scorers. On a Grade 5 pilot these reach Cohen’s ąppa up to 0.92 on conventions.</abstract>
    <identifier type="citekey">barber-etal-2026-multi</identifier>
    <location>
        <url>https://aclanthology.org/2026.aimecon-sessions.1/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1</start>
            <end>8</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Agent LLM Annotation and Scoring for Training Fine-Grained K-12 Writing-Feedback Models
%A Barber, Justin O.
%A Hemenway, Michael P.
%A Bellows, Martha
%A Lottridge, Susan
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-2-4
%F barber-etal-2026-multi
%X Fine-grained formative writing feedback needs dense, standards-aligned labels that human annotation cannot supply at scale. We describe a multi-agent LLM pipeline producing verified silver labels, and then train small deterministic transformer scorers. On a Grade 5 pilot these reach Cohen’s ąppa up to 0.92 on conventions.
%U https://aclanthology.org/2026.aimecon-sessions.1/
%P 1-8

Markdown (Informal)

[Multi-Agent LLM Annotation and Scoring for Training Fine-Grained K-12 Writing-Feedback Models](https://aclanthology.org/2026.aimecon-sessions.1/) (Barber et al., AIME-Con 2026)

• Multi-Agent LLM Annotation and Scoring for Training Fine-Grained K-12 Writing-Feedback Models (Barber et al., AIME-Con 2026)

ACL

• Justin O Barber, Michael P Hemenway, Martha Bellows, and Susan Lottridge. 2026. Multi-Agent LLM Annotation and Scoring for Training Fine-Grained K-12 Writing-Feedback Models. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 1–8, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).