@inproceedings{achamaleh-etal-2025-cic,
title = "{CIC}-{NLP}@{D}ravidian{L}ang{T}ech 2025: Detecting {AI}-generated Product Reviews in {D}ravidian Languages",
author = "Achamaleh, Tewodros and
Abiola, Tolulope Olalekan and
Kawo, Lemlem Eyob and
Mebraihtu, Mikiyas and
Sidorov, Grigori",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Rajiakodi, Saranya and
Palani, Balasubramanian and
Subramanian, Malliga and
Cn, Subalalitha and
Chinnappa, Dhivya",
booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = may,
year = "2025",
address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dravidianlangtech-1.88/",
doi = "10.18653/v1/2025.dravidianlangtech-1.88",
pages = "502--507",
ISBN = "979-8-89176-228-2",
abstract = "AI-generated text now matches human writing so well that telling them apart is very difficult. Our CIC-NLP team submits results for the DravidianLangTech@NAACL 2025 shared task to reveal AI-generated product reviews in Dravidian languages. We performed a binary classification task with XLM-RoBERTa-Base using the DravidianLangTech@NAACL 2025 datasets offered by the event organizers. Through training the model correctly, our tests could tell between human and AI-generated reviews with scores of 0.96 for Tamil and 0.88 for Malayalam in the evaluation test set. This paper presents detailed information about preprocessing, model architecture, hyperparameter fine-tuning settings, the experimental process, and the results. The source code is available on GitHub1."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="achamaleh-etal-2025-cic">
<titleInfo>
<title>CIC-NLP@DravidianLangTech 2025: Detecting AI-generated Product Reviews in Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tewodros</namePart>
<namePart type="family">Achamaleh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tolulope</namePart>
<namePart type="given">Olalekan</namePart>
<namePart type="family">Abiola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemlem</namePart>
<namePart type="given">Eyob</namePart>
<namePart type="family">Kawo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikiyas</namePart>
<namePart type="family">Mebraihtu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-228-2</identifier>
</relatedItem>
<abstract>AI-generated text now matches human writing so well that telling them apart is very difficult. Our CIC-NLP team submits results for the DravidianLangTech@NAACL 2025 shared task to reveal AI-generated product reviews in Dravidian languages. We performed a binary classification task with XLM-RoBERTa-Base using the DravidianLangTech@NAACL 2025 datasets offered by the event organizers. Through training the model correctly, our tests could tell between human and AI-generated reviews with scores of 0.96 for Tamil and 0.88 for Malayalam in the evaluation test set. This paper presents detailed information about preprocessing, model architecture, hyperparameter fine-tuning settings, the experimental process, and the results. The source code is available on GitHub1.</abstract>
<identifier type="citekey">achamaleh-etal-2025-cic</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.88</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.88/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>502</start>
<end>507</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIC-NLP@DravidianLangTech 2025: Detecting AI-generated Product Reviews in Dravidian Languages
%A Achamaleh, Tewodros
%A Abiola, Tolulope Olalekan
%A Kawo, Lemlem Eyob
%A Mebraihtu, Mikiyas
%A Sidorov, Grigori
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Rajiakodi, Saranya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Cn, Subalalitha
%Y Chinnappa, Dhivya
%S Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2025
%8 May
%I Association for Computational Linguistics
%C Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico
%@ 979-8-89176-228-2
%F achamaleh-etal-2025-cic
%X AI-generated text now matches human writing so well that telling them apart is very difficult. Our CIC-NLP team submits results for the DravidianLangTech@NAACL 2025 shared task to reveal AI-generated product reviews in Dravidian languages. We performed a binary classification task with XLM-RoBERTa-Base using the DravidianLangTech@NAACL 2025 datasets offered by the event organizers. Through training the model correctly, our tests could tell between human and AI-generated reviews with scores of 0.96 for Tamil and 0.88 for Malayalam in the evaluation test set. This paper presents detailed information about preprocessing, model architecture, hyperparameter fine-tuning settings, the experimental process, and the results. The source code is available on GitHub1.
%R 10.18653/v1/2025.dravidianlangtech-1.88
%U https://aclanthology.org/2025.dravidianlangtech-1.88/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.88
%P 502-507
Markdown (Informal)
[CIC-NLP@DravidianLangTech 2025: Detecting AI-generated Product Reviews in Dravidian Languages](https://aclanthology.org/2025.dravidianlangtech-1.88/) (Achamaleh et al., DravidianLangTech 2025)
ACL
- Tewodros Achamaleh, Tolulope Olalekan Abiola, Lemlem Eyob Kawo, Mikiyas Mebraihtu, and Grigori Sidorov. 2025. CIC-NLP@DravidianLangTech 2025: Detecting AI-generated Product Reviews in Dravidian Languages. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 502–507, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.