@inproceedings{ali-etal-2025-hlu,
title = "{HLU}: Human Vs {LLM} Generated Text Detection Dataset for {U}rdu at Multiple Granularities",
author = "Ali, Iqra and
Atuhurra, Jesse and
Kamigaito, Hidetaka and
Watanabe, Taro",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.235/",
pages = "3495--3510",
abstract = "The rise of large language models (LLMs) generating human-like text has raised concerns about misuse, especially in low-resource languages like Urdu. To address this gap, we introduce the HLU dataset, which consists of three datasets: Document, Paragraph, and Sentence level. The document-level dataset contains 1,014 instances of human-written and LLM-generated articles across 13 domains, while the paragraph and sentence-level datasets each contain 667 instances. We conducted both human and automatic evaluations. In the human evaluation, the average accuracy at the document level was 35{\%}, while at the paragraph and sentence levels, accuracies were 75.68{\%} and 88.45{\%}, respectively. For automatic evaluation, we finetuned the XLMRoBERTa model for both monolingual and multilingual settings achieving consistent results in both. Additionally, we assessed the performance of GPT4 and Claude3Opus using zero-shot prompting. Our experiments and evaluations indicate that distinguishing between human and machine-generated text is challenging for both humans and LLMs, marking a significant step in addressing this issue in Urdu."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-etal-2025-hlu">
<titleInfo>
<title>HLU: Human Vs LLM Generated Text Detection Dataset for Urdu at Multiple Granularities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iqra</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Atuhurra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rise of large language models (LLMs) generating human-like text has raised concerns about misuse, especially in low-resource languages like Urdu. To address this gap, we introduce the HLU dataset, which consists of three datasets: Document, Paragraph, and Sentence level. The document-level dataset contains 1,014 instances of human-written and LLM-generated articles across 13 domains, while the paragraph and sentence-level datasets each contain 667 instances. We conducted both human and automatic evaluations. In the human evaluation, the average accuracy at the document level was 35%, while at the paragraph and sentence levels, accuracies were 75.68% and 88.45%, respectively. For automatic evaluation, we finetuned the XLMRoBERTa model for both monolingual and multilingual settings achieving consistent results in both. Additionally, we assessed the performance of GPT4 and Claude3Opus using zero-shot prompting. Our experiments and evaluations indicate that distinguishing between human and machine-generated text is challenging for both humans and LLMs, marking a significant step in addressing this issue in Urdu.</abstract>
<identifier type="citekey">ali-etal-2025-hlu</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.235/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>3495</start>
<end>3510</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HLU: Human Vs LLM Generated Text Detection Dataset for Urdu at Multiple Granularities
%A Ali, Iqra
%A Atuhurra, Jesse
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ali-etal-2025-hlu
%X The rise of large language models (LLMs) generating human-like text has raised concerns about misuse, especially in low-resource languages like Urdu. To address this gap, we introduce the HLU dataset, which consists of three datasets: Document, Paragraph, and Sentence level. The document-level dataset contains 1,014 instances of human-written and LLM-generated articles across 13 domains, while the paragraph and sentence-level datasets each contain 667 instances. We conducted both human and automatic evaluations. In the human evaluation, the average accuracy at the document level was 35%, while at the paragraph and sentence levels, accuracies were 75.68% and 88.45%, respectively. For automatic evaluation, we finetuned the XLMRoBERTa model for both monolingual and multilingual settings achieving consistent results in both. Additionally, we assessed the performance of GPT4 and Claude3Opus using zero-shot prompting. Our experiments and evaluations indicate that distinguishing between human and machine-generated text is challenging for both humans and LLMs, marking a significant step in addressing this issue in Urdu.
%U https://aclanthology.org/2025.coling-main.235/
%P 3495-3510
Markdown (Informal)
[HLU: Human Vs LLM Generated Text Detection Dataset for Urdu at Multiple Granularities](https://aclanthology.org/2025.coling-main.235/) (Ali et al., COLING 2025)
ACL