Saved in:
Bibliographic Details
Main Authors: Samant, Yashad, Becker, Lee, Hellman, Scott, Behan, Bradley, Hughes, Sarah, Southerland, Joshua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.08355
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914031277703168
author Samant, Yashad
Becker, Lee
Hellman, Scott
Behan, Bradley
Hughes, Sarah
Southerland, Joshua
author_facet Samant, Yashad
Becker, Lee
Hellman, Scott
Behan, Bradley
Hughes, Sarah
Southerland, Joshua
contents In high-stakes English Language Assessments, low-skill test takers may employ memorized materials called ``templates'' on essay questions to ``game'' or fool the automated scoring system. In this study, we introduce the automated detection of inauthentic, templated responses (AuDITR) task, describe a machine learning-based approach to this task and illustrate the importance of regularly updating these models in production.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08355
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic Detection of Inauthentic Templated Responses in English Language Assessments
Samant, Yashad
Becker, Lee
Hellman, Scott
Behan, Bradley
Hughes, Sarah
Southerland, Joshua
Computation and Language
Artificial Intelligence
In high-stakes English Language Assessments, low-skill test takers may employ memorized materials called ``templates'' on essay questions to ``game'' or fool the automated scoring system. In this study, we introduce the automated detection of inauthentic, templated responses (AuDITR) task, describe a machine learning-based approach to this task and illustrate the importance of regularly updating these models in production.
title Automatic Detection of Inauthentic Templated Responses in English Language Assessments
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.08355