@inproceedings{agrahari-ranbir-singh-2025-osint,
title = "{OSINT} at {G}en{AI} Detection Task 1: Multilingual {MGT} Detection: Leveraging Cross-Lingual Adaptation for Robust {LLM}s Text Identification",
author = "Agrahari, Shifali and
Ranbir Singh, Sanasam",
editor = "Alam, Firoj and
Nakov, Preslav and
Habash, Nizar and
Gurevych, Iryna and
Chowdhury, Shammur and
Shelmanov, Artem and
Wang, Yuxia and
Artemova, Ekaterina and
Kutlu, Mucahid and
Mikros, George",
booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2025.genaidetect-1.18/",
pages = "184--190",
abstract = "Detecting AI-generated text has become in- creasingly prominent. This paper presents our solution for the DAIGenC Task 1 Subtask 2, where we address the challenge of distin- guishing human-authored text from machine- generated content, especially in multilingual contexts. We introduce Multi-Task Detection (MLDet), a model that leverages Cross-Lingual Adaptation and Model Generalization strate- gies for Multilingual Machine-Generated Text (MGT) detection. By combining language- specific embeddings with fusion techniques, MLDet creates a unified, language-agnostic feature representation, enhancing its ability to generalize across diverse languages and mod- els. Our approach demonstrates strong perfor- mance, achieving macro and micro F1 scores of 0.7067 and 0.7187, respectively, and ranking 15th in the competition1. We also evaluate our model across datasets generated by different distinct models in many languages, showcasing its robustness in multilingual and cross-model scenarios."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agrahari-ranbir-singh-2025-osint">
<titleInfo>
<title>OSINT at GenAI Detection Task 1: Multilingual MGT Detection: Leveraging Cross-Lingual Adaptation for Robust LLMs Text Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shifali</namePart>
<namePart type="family">Agrahari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanasam</namePart>
<namePart type="family">Ranbir Singh</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 1stWorkshop on GenAI Content Detection (GenAIDetect)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Mikros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detecting AI-generated text has become in- creasingly prominent. This paper presents our solution for the DAIGenC Task 1 Subtask 2, where we address the challenge of distin- guishing human-authored text from machine- generated content, especially in multilingual contexts. We introduce Multi-Task Detection (MLDet), a model that leverages Cross-Lingual Adaptation and Model Generalization strate- gies for Multilingual Machine-Generated Text (MGT) detection. By combining language- specific embeddings with fusion techniques, MLDet creates a unified, language-agnostic feature representation, enhancing its ability to generalize across diverse languages and mod- els. Our approach demonstrates strong perfor- mance, achieving macro and micro F1 scores of 0.7067 and 0.7187, respectively, and ranking 15th in the competition1. We also evaluate our model across datasets generated by different distinct models in many languages, showcasing its robustness in multilingual and cross-model scenarios.</abstract>
<identifier type="citekey">agrahari-ranbir-singh-2025-osint</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.18/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>184</start>
<end>190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OSINT at GenAI Detection Task 1: Multilingual MGT Detection: Leveraging Cross-Lingual Adaptation for Robust LLMs Text Identification
%A Agrahari, Shifali
%A Ranbir Singh, Sanasam
%Y Alam, Firoj
%Y Nakov, Preslav
%Y Habash, Nizar
%Y Gurevych, Iryna
%Y Chowdhury, Shammur
%Y Shelmanov, Artem
%Y Wang, Yuxia
%Y Artemova, Ekaterina
%Y Kutlu, Mucahid
%Y Mikros, George
%S Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
%D 2025
%8 January
%I International Conference on Computational Linguistics
%C Abu Dhabi, UAE
%F agrahari-ranbir-singh-2025-osint
%X Detecting AI-generated text has become in- creasingly prominent. This paper presents our solution for the DAIGenC Task 1 Subtask 2, where we address the challenge of distin- guishing human-authored text from machine- generated content, especially in multilingual contexts. We introduce Multi-Task Detection (MLDet), a model that leverages Cross-Lingual Adaptation and Model Generalization strate- gies for Multilingual Machine-Generated Text (MGT) detection. By combining language- specific embeddings with fusion techniques, MLDet creates a unified, language-agnostic feature representation, enhancing its ability to generalize across diverse languages and mod- els. Our approach demonstrates strong perfor- mance, achieving macro and micro F1 scores of 0.7067 and 0.7187, respectively, and ranking 15th in the competition1. We also evaluate our model across datasets generated by different distinct models in many languages, showcasing its robustness in multilingual and cross-model scenarios.
%U https://aclanthology.org/2025.genaidetect-1.18/
%P 184-190
Markdown (Informal)
[OSINT at GenAI Detection Task 1: Multilingual MGT Detection: Leveraging Cross-Lingual Adaptation for Robust LLMs Text Identification](https://aclanthology.org/2025.genaidetect-1.18/) (Agrahari & Ranbir Singh, GenAIDetect 2025)
ACL