AI-generated Text Detection: A Multifaceted Approach to Binary and Multiclass Classification

TL;DR

This paper presents neural architectures for detecting AI-generated text and attributing it to specific models, achieving high accuracy in shared tasks to promote responsible use of language models.

Contribution

It introduces two neural models for binary and multiclass classification of AI-generated text, with optimized and simplified variants, advancing detection capabilities.

Findings

Optimized model for AI detection achieved 0.994 F1 score.

Simpler model for model attribution achieved 0.627 F1 score.

Both models ranked fifth in their respective tasks at AAAI 2025.

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating text that closely resembles human writing across a wide range of styles and genres. However, such capabilities are prone to potential misuse, such as fake news generation, spam email creation, and misuse in academic assignments. As a result, accurate detection of AI-generated text and identification of the model that generated it are crucial for maintaining the responsible use of LLMs. In this work, we addressed two sub-tasks put forward by the Defactify workshop under AI-Generated Text Detection shared task at the Association for the Advancement of Artificial Intelligence (AAAI 2025): Task A involved distinguishing between human-authored or AI-generated text, while Task B focused on attributing text to its originating language model. For each task, we proposed two neural architectures: an optimized model and a simpler variant. For Task A, the optimized neural architecture achieved fifth place with $F1$ score of 0.994, and for Task B, the simpler neural architecture also ranked fifth place with $F1$ score of 0.627.