@inproceedings{bhandarkar-etal-2025-aaig,
title = "{AAIG} at {G}en{AI} Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for {AI} Content Detection",
author = "Bhandarkar, Avanti and
Wilson, Ronald and
Woodard, Damon",
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-1.23/",
pages = "218--224",
abstract = "This paper presents a lightweight and efficient approach to AI-generated content detection using small autoregressive fine-tuned decoders (AFDs) for secure, on-device deployment. Motivated by resource-efficiency, syntactic awareness, and bias mitigation, our model employs small language models (SLMs) with autoregressive pre-training and loss fusion to accurately distinguish between human and AI-generated content while significantly reducing computational demands. The system achieved highest macro-F1 score of 0.8186, with the submitted model scoring 0.7874{---}both significantly outperforming the task baseline while reducing model parameters by {\textasciitilde}60{\%}. Notably, our approach mitigates biases, improving recall for human-authored text by over 60{\%}. Ranking 8th out of 36 participants, these results confirm the feasibility and competitiveness of small AFDs in challenging, adversarial settings, making them ideal for privacy-preserving, on-device deployment suitable for real-world applications."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhandarkar-etal-2025-aaig">
<titleInfo>
<title>AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avanti</namePart>
<namePart type="family">Bhandarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronald</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damon</namePart>
<namePart type="family">Woodard</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>This paper presents a lightweight and efficient approach to AI-generated content detection using small autoregressive fine-tuned decoders (AFDs) for secure, on-device deployment. Motivated by resource-efficiency, syntactic awareness, and bias mitigation, our model employs small language models (SLMs) with autoregressive pre-training and loss fusion to accurately distinguish between human and AI-generated content while significantly reducing computational demands. The system achieved highest macro-F1 score of 0.8186, with the submitted model scoring 0.7874—both significantly outperforming the task baseline while reducing model parameters by ~60%. Notably, our approach mitigates biases, improving recall for human-authored text by over 60%. Ranking 8th out of 36 participants, these results confirm the feasibility and competitiveness of small AFDs in challenging, adversarial settings, making them ideal for privacy-preserving, on-device deployment suitable for real-world applications.</abstract>
<identifier type="citekey">bhandarkar-etal-2025-aaig</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.23/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>218</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection
%A Bhandarkar, Avanti
%A Wilson, Ronald
%A Woodard, Damon
%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 bhandarkar-etal-2025-aaig
%X This paper presents a lightweight and efficient approach to AI-generated content detection using small autoregressive fine-tuned decoders (AFDs) for secure, on-device deployment. Motivated by resource-efficiency, syntactic awareness, and bias mitigation, our model employs small language models (SLMs) with autoregressive pre-training and loss fusion to accurately distinguish between human and AI-generated content while significantly reducing computational demands. The system achieved highest macro-F1 score of 0.8186, with the submitted model scoring 0.7874—both significantly outperforming the task baseline while reducing model parameters by ~60%. Notably, our approach mitigates biases, improving recall for human-authored text by over 60%. Ranking 8th out of 36 participants, these results confirm the feasibility and competitiveness of small AFDs in challenging, adversarial settings, making them ideal for privacy-preserving, on-device deployment suitable for real-world applications.
%U https://aclanthology.org/2025.genaidetect-1.23/
%P 218-224
Markdown (Informal)
[AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection](https://aclanthology.org/2025.genaidetect-1.23/) (Bhandarkar et al., GenAIDetect 2025)
ACL