AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection

Avanti Bhandarkar, Ronald Wilson, Damon Woodard


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.
Anthology ID:
2025.genaidetect-1.23
Volume:
Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Firoj Alam, Preslav Nakov, Nizar Habash, Iryna Gurevych, Shammur Chowdhury, Artem Shelmanov, Yuxia Wang, Ekaterina Artemova, Mucahid Kutlu, George Mikros
Venues:
GenAIDetect | WS
SIG:
Publisher:
International Conference on Computational Linguistics
Note:
Pages:
218–224
Language:
URL:
https://aclanthology.org/2025.genaidetect-1.23/
DOI:
Bibkey:
Cite (ACL):
Avanti Bhandarkar, Ronald Wilson, and Damon Woodard. 2025. AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 218–224, Abu Dhabi, UAE. International Conference on Computational Linguistics.
Cite (Informal):
AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection (Bhandarkar et al., GenAIDetect 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaidetect-1.23.pdf