@inproceedings{doan-inui-2025-grape,
title = "Grape at {G}en{AI} Detection Task 1: Leveraging Compact Models and Linguistic Features for Robust Machine-Generated Text Detection",
author = "Doan, Nhi Hoai and
Inui, Kentaro",
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-1.22/",
pages = "209--217",
abstract = "In this project, we aim to address two subtasks of Task 1: Binary Multilingual Machine-Generated Text (MGT) Detection (Human vs. Machine) as part of the COLING 2025 Workshop on MGT Detection (Wang et al., 2025) using different approaches. The first method involves separately fine-tuning small language models tailored to the specific subtask. The second approach builds on this methodology by incorporating linguistic, syntactic, and semantic features, leveraging ensemble learning to integrate these features with model predictions for more robust classification. By evaluating and comparing these approaches, we aim to identify the most effective techniques for detecting machine-generated content across languages, providing insights into improving automated verification tools amidst the rapid growth of LLM-generated text in digital spaces."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doan-inui-2025-grape">
<titleInfo>
<title>Grape at GenAI Detection Task 1: Leveraging Compact Models and Linguistic Features for Robust Machine-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nhi</namePart>
<namePart type="given">Hoai</namePart>
<namePart type="family">Doan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</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>In this project, we aim to address two subtasks of Task 1: Binary Multilingual Machine-Generated Text (MGT) Detection (Human vs. Machine) as part of the COLING 2025 Workshop on MGT Detection (Wang et al., 2025) using different approaches. The first method involves separately fine-tuning small language models tailored to the specific subtask. The second approach builds on this methodology by incorporating linguistic, syntactic, and semantic features, leveraging ensemble learning to integrate these features with model predictions for more robust classification. By evaluating and comparing these approaches, we aim to identify the most effective techniques for detecting machine-generated content across languages, providing insights into improving automated verification tools amidst the rapid growth of LLM-generated text in digital spaces.</abstract>
<identifier type="citekey">doan-inui-2025-grape</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.22/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>209</start>
<end>217</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grape at GenAI Detection Task 1: Leveraging Compact Models and Linguistic Features for Robust Machine-Generated Text Detection
%A Doan, Nhi Hoai
%A Inui, Kentaro
%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 doan-inui-2025-grape
%X In this project, we aim to address two subtasks of Task 1: Binary Multilingual Machine-Generated Text (MGT) Detection (Human vs. Machine) as part of the COLING 2025 Workshop on MGT Detection (Wang et al., 2025) using different approaches. The first method involves separately fine-tuning small language models tailored to the specific subtask. The second approach builds on this methodology by incorporating linguistic, syntactic, and semantic features, leveraging ensemble learning to integrate these features with model predictions for more robust classification. By evaluating and comparing these approaches, we aim to identify the most effective techniques for detecting machine-generated content across languages, providing insights into improving automated verification tools amidst the rapid growth of LLM-generated text in digital spaces.
%U https://aclanthology.org/2025.genaidetect-1.22/
%P 209-217
Markdown (Informal)
[Grape at GenAI Detection Task 1: Leveraging Compact Models and Linguistic Features for Robust Machine-Generated Text Detection](https://aclanthology.org/2025.genaidetect-1.22/) (Doan & Inui, GenAIDetect 2025)
ACL