Overview of the 2024 ALTA Shared Task: Detect Automatic AI-Generated Sentences for Human-AI Hybrid Articles
Diego Mollá, Qiongkai Xu, Zijie Zeng, Zhuang Li
TL;DR
This work introduces the 2024 ALTA shared task focused on sentence-level detection of AI-generated content within hybrid human–AI articles. By leveraging a public hybrid-text dataset and a private test set across academic and news domains, the authors implement a phased CodaLab evaluation and establish strong baselines, including a Context-Aware BERT and a TF-IDF classifier. The participating systems achieve notable performance, with top teams reaching high Cohen's Kappa scores, illustrating the viability of fine-grained detection in real-world collaborative writing. The study advances boundary-aware, domain-sensitive AI content detection and sets benchmarks for journalism and academic writing contexts.
Abstract
The ALTA shared tasks have been running annually since 2010. In 2024, the purpose of the task is to detect machine-generated text in a hybrid setting where the text may contain portions of human text and portions machine-generated. In this paper, we present the task, the evaluation criteria, and the results of the systems participating in the shared task.