@inproceedings{baffour-etal-2023-analyzing,
title = "Analyzing Bias in Large Language Model Solutions for Assisted Writing Feedback Tools: Lessons from the Feedback Prize Competition Series",
author = "Baffour, Perpetual and
Saxberg, Tor and
Crossley, Scott",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.21",
doi = "10.18653/v1/2023.bea-1.21",
pages = "242--246",
abstract = "This paper analyzes winning solutions from the Feedback Prize competition series hosted from 2021-2022. The competition sought to improve Assisted Writing Feedback Tools (AWFTs) by crowdsourcing Large Language Model (LLM) solutions for evaluating student writing. The winning models are freely available for incorporation into educational applications, but the models need to be assessed for performance and other factors. This study reports the performance accuracy of Feedback Prize-winning models based on demographic factors such as student race/ethnicity, economic disadvantage, and English Language Learner status. Two competitions are analyzed. The first, which focused on identifying discourse elements, demonstrated minimal bias based on students{'} demographic factors. However, the second competition, which aimed to predict discourse effectiveness, exhibited moderate bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baffour-etal-2023-analyzing">
<titleInfo>
<title>Analyzing Bias in Large Language Model Solutions for Assisted Writing Feedback Tools: Lessons from the Feedback Prize Competition Series</title>
</titleInfo>
<name type="personal">
<namePart type="given">Perpetual</namePart>
<namePart type="family">Baffour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tor</namePart>
<namePart type="family">Saxberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Crossley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper analyzes winning solutions from the Feedback Prize competition series hosted from 2021-2022. The competition sought to improve Assisted Writing Feedback Tools (AWFTs) by crowdsourcing Large Language Model (LLM) solutions for evaluating student writing. The winning models are freely available for incorporation into educational applications, but the models need to be assessed for performance and other factors. This study reports the performance accuracy of Feedback Prize-winning models based on demographic factors such as student race/ethnicity, economic disadvantage, and English Language Learner status. Two competitions are analyzed. The first, which focused on identifying discourse elements, demonstrated minimal bias based on students’ demographic factors. However, the second competition, which aimed to predict discourse effectiveness, exhibited moderate bias.</abstract>
<identifier type="citekey">baffour-etal-2023-analyzing</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.21</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.21</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>242</start>
<end>246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Bias in Large Language Model Solutions for Assisted Writing Feedback Tools: Lessons from the Feedback Prize Competition Series
%A Baffour, Perpetual
%A Saxberg, Tor
%A Crossley, Scott
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F baffour-etal-2023-analyzing
%X This paper analyzes winning solutions from the Feedback Prize competition series hosted from 2021-2022. The competition sought to improve Assisted Writing Feedback Tools (AWFTs) by crowdsourcing Large Language Model (LLM) solutions for evaluating student writing. The winning models are freely available for incorporation into educational applications, but the models need to be assessed for performance and other factors. This study reports the performance accuracy of Feedback Prize-winning models based on demographic factors such as student race/ethnicity, economic disadvantage, and English Language Learner status. Two competitions are analyzed. The first, which focused on identifying discourse elements, demonstrated minimal bias based on students’ demographic factors. However, the second competition, which aimed to predict discourse effectiveness, exhibited moderate bias.
%R 10.18653/v1/2023.bea-1.21
%U https://aclanthology.org/2023.bea-1.21
%U https://doi.org/10.18653/v1/2023.bea-1.21
%P 242-246
Markdown (Informal)
[Analyzing Bias in Large Language Model Solutions for Assisted Writing Feedback Tools: Lessons from the Feedback Prize Competition Series](https://aclanthology.org/2023.bea-1.21) (Baffour et al., BEA 2023)
ACL