Artificial Text Detection with Multiple Training Strategies

TL;DR

This paper presents a method using DeBERTa with multiple training strategies to detect artificially generated texts, achieving high accuracy and ranking second in the RuATD 2022 shared task.

Contribution

It introduces a novel approach combining DeBERTa and multiple training strategies specifically for Russian artificial text detection.

Findings

Effective detection of artificial texts demonstrated on RuATD dataset

Achieved second place in RuATD 2022 evaluation

Validated the robustness of the proposed method

Abstract

As the deep learning rapidly promote, the artificial texts created by generative models are commonly used in news and social media. However, such models can be abused to generate product reviews, fake news, and even fake political content. The paper proposes a solution for the Russian Artificial Text Detection in the Dialogue shared task 2022 (RuATD 2022) to distinguish which model within the list is used to generate this text. We introduce the DeBERTa pre-trained language model with multiple training strategies for this shared task. Extensive experiments conducted on the RuATD dataset validate the effectiveness of our proposed method. Moreover, our submission ranked second place in the evaluation phase for RuATD 2022 (Multi-Class).