@inproceedings{jung-etal-2025-optimizing,
title = "Optimizing Reliability Scoring for {ILSA}s",
author = "Jung, Ji Yoon and
Bezirhan, Ummugul and
von Davier, Matthias",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full 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-main.6/",
pages = "43--49",
ISBN = "979-8-218-84228-4",
abstract = "This study proposes an innovative method for evaluating cross-country scoring reliability (CCSR) in multilingual assessments, using hyperparameter optimization and a similarity-based weighted majority scoring within a single human scoring framework. Results show that this approach provides a cost-effective and comprehensive assessment of CCSR without the need for additional raters."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2025-optimizing">
<titleInfo>
<title>Optimizing Reliability Scoring for ILSAs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="given">Yoon</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ummugul</namePart>
<namePart type="family">Bezirhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">von Davier</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): 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">979-8-218-84228-4</identifier>
</relatedItem>
<abstract>This study proposes an innovative method for evaluating cross-country scoring reliability (CCSR) in multilingual assessments, using hyperparameter optimization and a similarity-based weighted majority scoring within a single human scoring framework. Results show that this approach provides a cost-effective and comprehensive assessment of CCSR without the need for additional raters.</abstract>
<identifier type="citekey">jung-etal-2025-optimizing</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-main.6/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>43</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimizing Reliability Scoring for ILSAs
%A Jung, Ji Yoon
%A Bezirhan, Ummugul
%A von Davier, Matthias
%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 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84228-4
%F jung-etal-2025-optimizing
%X This study proposes an innovative method for evaluating cross-country scoring reliability (CCSR) in multilingual assessments, using hyperparameter optimization and a similarity-based weighted majority scoring within a single human scoring framework. Results show that this approach provides a cost-effective and comprehensive assessment of CCSR without the need for additional raters.
%U https://aclanthology.org/2025.aimecon-main.6/
%P 43-49
Markdown (Informal)
[Optimizing Reliability Scoring for ILSAs](https://aclanthology.org/2025.aimecon-main.6/) (Jung et al., AIME-Con 2025)
ACL
- Ji Yoon Jung, Ummugul Bezirhan, and Matthias von Davier. 2025. Optimizing Reliability Scoring for ILSAs. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 43–49, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).