@inproceedings{palermo-etal-2025-operational,
title = "Operational Alignment of Confidence-Based Flagging Methods in Automated Scoring",
author = "Palermo, Corey and
Chen, Troy and
Wibowo, Arianto",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers",
month = oct,
year = "2025",
address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2025.aimecon-sessions.6/",
pages = "56--60",
ISBN = "979-8-218-84230-7",
abstract = "In hybrid scoring systems, confidence thresholds determine which responses receive human review. This study evaluates a relative (within-batch) thresholding method against an absolute benchmark across ten items. Results show near-perfect agreement and modest distributional differences, supporting the relative method{'}s validity as a scalable, operationally viable approach for flagging low-confidence responses."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="palermo-etal-2025-operational">
<titleInfo>
<title>Operational Alignment of Confidence-Based Flagging Methods in Automated Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Corey</namePart>
<namePart type="family">Palermo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Troy</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianto</namePart>
<namePart type="family">Wibowo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</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">979-8-218-84230-7</identifier>
</relatedItem>
<abstract>In hybrid scoring systems, confidence thresholds determine which responses receive human review. This study evaluates a relative (within-batch) thresholding method against an absolute benchmark across ten items. Results show near-perfect agreement and modest distributional differences, supporting the relative method’s validity as a scalable, operationally viable approach for flagging low-confidence responses.</abstract>
<identifier type="citekey">palermo-etal-2025-operational</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-sessions.6/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>56</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Operational Alignment of Confidence-Based Flagging Methods in Automated Scoring
%A Palermo, Corey
%A Chen, Troy
%A Wibowo, Arianto
%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 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84230-7
%F palermo-etal-2025-operational
%X In hybrid scoring systems, confidence thresholds determine which responses receive human review. This study evaluates a relative (within-batch) thresholding method against an absolute benchmark across ten items. Results show near-perfect agreement and modest distributional differences, supporting the relative method’s validity as a scalable, operationally viable approach for flagging low-confidence responses.
%U https://aclanthology.org/2025.aimecon-sessions.6/
%P 56-60
Markdown (Informal)
[Operational Alignment of Confidence-Based Flagging Methods in Automated Scoring](https://aclanthology.org/2025.aimecon-sessions.6/) (Palermo et al., AIME-Con 2025)
ACL
- Corey Palermo, Troy Chen, and Arianto Wibowo. 2025. Operational Alignment of Confidence-Based Flagging Methods in Automated Scoring. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 56–60, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).