@inproceedings{meng-etal-2025-identifying,
title = "Identifying Biases in Large Language Model Assessment of Linguistically Diverse Texts",
author = "Meng, Lionel Hsien and
Karumbaiah, Shamya and
Saravanan, Vivek and
Bolt, Daniel",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress",
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-wip.25/",
pages = "204--210",
ISBN = "979-8-218-84229-1",
abstract = "The development of Large Language Models (LLMs) to assess student text responses is rapidly progressing but evaluating whether LLMs equitably assess multilingual learner responses is an important precursor to adoption. Our study provides an example procedure for identifying and quantifying bias in LLM assessment of student essay responses."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-etal-2025-identifying">
<titleInfo>
<title>Identifying Biases in Large Language Model Assessment of Linguistically Diverse Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lionel</namePart>
<namePart type="given">Hsien</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamya</namePart>
<namePart type="family">Karumbaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Saravanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Bolt</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): Works in Progress</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">979-8-218-84229-1</identifier>
</relatedItem>
<abstract>The development of Large Language Models (LLMs) to assess student text responses is rapidly progressing but evaluating whether LLMs equitably assess multilingual learner responses is an important precursor to adoption. Our study provides an example procedure for identifying and quantifying bias in LLM assessment of student essay responses.</abstract>
<identifier type="citekey">meng-etal-2025-identifying</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-wip.25/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>204</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Biases in Large Language Model Assessment of Linguistically Diverse Texts
%A Meng, Lionel Hsien
%A Karumbaiah, Shamya
%A Saravanan, Vivek
%A Bolt, Daniel
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84229-1
%F meng-etal-2025-identifying
%X The development of Large Language Models (LLMs) to assess student text responses is rapidly progressing but evaluating whether LLMs equitably assess multilingual learner responses is an important precursor to adoption. Our study provides an example procedure for identifying and quantifying bias in LLM assessment of student essay responses.
%U https://aclanthology.org/2025.aimecon-wip.25/
%P 204-210
Markdown (Informal)
[Identifying Biases in Large Language Model Assessment of Linguistically Diverse Texts](https://aclanthology.org/2025.aimecon-wip.25/) (Meng et al., AIME-Con 2025)
ACL
- Lionel Hsien Meng, Shamya Karumbaiah, Vivek Saravanan, and Daniel Bolt. 2025. Identifying Biases in Large Language Model Assessment of Linguistically Diverse Texts. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 204–210, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).