@inproceedings{xiong-etal-2026-language,
title = "When Language Becomes a Shortcut in Automated Short-Answer Scoring",
author = "Xiong, Xiaomeng and
Huggins-Manley, Corinne and
Shin, Jinnie and
Grant, Christan",
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 = "2026",
address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2026.aimecon-sessions.16/",
pages = "146--163",
ISBN = "979-8-9983004-2-4",
abstract = "Automated short-answer scoring should reflect substantive content rather than linguistic form. Using controlled rewrites of 743 ASAP-SAS responses, we compare six fine-tuned encoders and 11 LLMs. Encoder scores increased with linguistic complexity, especially for lower-scoring responses, whereas LLMs showed heterogeneous patterns, revealing model-specific construct-irrelevant scoring signals."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiong-etal-2026-language">
<titleInfo>
<title>When Language Becomes a Shortcut in Automated Short-Answer Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaomeng</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corinne</namePart>
<namePart type="family">Huggins-Manley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinnie</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christan</namePart>
<namePart type="family">Grant</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>Automated short-answer scoring should reflect substantive content rather than linguistic form. Using controlled rewrites of 743 ASAP-SAS responses, we compare six fine-tuned encoders and 11 LLMs. Encoder scores increased with linguistic complexity, especially for lower-scoring responses, whereas LLMs showed heterogeneous patterns, revealing model-specific construct-irrelevant scoring signals.</abstract>
<identifier type="citekey">xiong-etal-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-sessions.16/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>146</start>
<end>163</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Language Becomes a Shortcut in Automated Short-Answer Scoring
%A Xiong, Xiaomeng
%A Huggins-Manley, Corinne
%A Shin, Jinnie
%A Grant, Christan
%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 xiong-etal-2026-language
%X Automated short-answer scoring should reflect substantive content rather than linguistic form. Using controlled rewrites of 743 ASAP-SAS responses, we compare six fine-tuned encoders and 11 LLMs. Encoder scores increased with linguistic complexity, especially for lower-scoring responses, whereas LLMs showed heterogeneous patterns, revealing model-specific construct-irrelevant scoring signals.
%U https://aclanthology.org/2026.aimecon-sessions.16/
%P 146-163
Markdown (Informal)
[When Language Becomes a Shortcut in Automated Short-Answer Scoring](https://aclanthology.org/2026.aimecon-sessions.16/) (Xiong et al., AIME-Con 2026)
ACL
- Xiaomeng Xiong, Corinne Huggins-Manley, Jinnie Shin, and Christan Grant. 2026. When Language Becomes a Shortcut in Automated Short-Answer Scoring. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 146–163, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).