@inproceedings{hendi-2026-xlmr,
title = "{XLMR}-{U}rdu at {A}bjad{G}en{E}val Shared Task: A Data-Centric Transformer-Based Approach for {AI}-Generated {U}rdu Text Detection",
author = "Hendi, Mohannad Mohammad",
booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.abjadnlp-1.56/",
pages = "461--467",
abstract = "The rapid advancement of large language models (LLMs) has led to a substantial increase in automatically generated textual content, raising concerns regarding misinformation, plagiarism, and authorship verification. These challenges are particularly pronounced for low-resource languages such as Urdu, where limited annotated data and complex linguistic properties hinder robust detection. In this paper, we present a transformer-based approach for binary classification of human-written versus AI-generated Urdu text, developed for the AbjadGenEval Task 2 shared task. Beyond model fine-tuning, we adopt a data-centric perspective, emphasizing dataset diagnostics, document-level inference, and calibration strategies. Our system achieves strong performance on the official test set, with an F1-score of 88.68{\%} and balanced accuracy of 88.71{\%}. Through empirical analysis, we demonstrate that dataset characteristics and generator-specific artifacts play a dominant role in model generalization, highlighting critical directions for future research in low-resource AI-generated text detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hendi-2026-xlmr">
<titleInfo>
<title>XLMR-Urdu at AbjadGenEval Shared Task: A Data-Centric Transformer-Based Approach for AI-Generated Urdu Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohannad</namePart>
<namePart type="given">Mohammad</namePart>
<namePart type="family">Hendi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid advancement of large language models (LLMs) has led to a substantial increase in automatically generated textual content, raising concerns regarding misinformation, plagiarism, and authorship verification. These challenges are particularly pronounced for low-resource languages such as Urdu, where limited annotated data and complex linguistic properties hinder robust detection. In this paper, we present a transformer-based approach for binary classification of human-written versus AI-generated Urdu text, developed for the AbjadGenEval Task 2 shared task. Beyond model fine-tuning, we adopt a data-centric perspective, emphasizing dataset diagnostics, document-level inference, and calibration strategies. Our system achieves strong performance on the official test set, with an F1-score of 88.68% and balanced accuracy of 88.71%. Through empirical analysis, we demonstrate that dataset characteristics and generator-specific artifacts play a dominant role in model generalization, highlighting critical directions for future research in low-resource AI-generated text detection.</abstract>
<identifier type="citekey">hendi-2026-xlmr</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.56/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>461</start>
<end>467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XLMR-Urdu at AbjadGenEval Shared Task: A Data-Centric Transformer-Based Approach for AI-Generated Urdu Text Detection
%A Hendi, Mohannad Mohammad
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F hendi-2026-xlmr
%X The rapid advancement of large language models (LLMs) has led to a substantial increase in automatically generated textual content, raising concerns regarding misinformation, plagiarism, and authorship verification. These challenges are particularly pronounced for low-resource languages such as Urdu, where limited annotated data and complex linguistic properties hinder robust detection. In this paper, we present a transformer-based approach for binary classification of human-written versus AI-generated Urdu text, developed for the AbjadGenEval Task 2 shared task. Beyond model fine-tuning, we adopt a data-centric perspective, emphasizing dataset diagnostics, document-level inference, and calibration strategies. Our system achieves strong performance on the official test set, with an F1-score of 88.68% and balanced accuracy of 88.71%. Through empirical analysis, we demonstrate that dataset characteristics and generator-specific artifacts play a dominant role in model generalization, highlighting critical directions for future research in low-resource AI-generated text detection.
%U https://aclanthology.org/2026.abjadnlp-1.56/
%P 461-467
Markdown (Informal)
[XLMR-Urdu at AbjadGenEval Shared Task: A Data-Centric Transformer-Based Approach for AI-Generated Urdu Text Detection](https://aclanthology.org/2026.abjadnlp-1.56/) (Hendi, AbjadNLP 2026)
ACL