M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection
This addresses the societal problem of potential misuse of LLM-generated texts in journalism, education, and academia, but is incremental as it primarily provides a dataset and highlights existing challenges.
The study tackled the problem of detecting machine-generated text by introducing the M4 benchmark, a large-scale multi-generator, multi-domain, and multi-lingual corpus, and found that detectors struggle to generalize to unseen domains or LLMs, often misclassifying machine-generated text as human-written.
Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries. However, this has also raised concerns about the potential misuse of such texts in journalism, education, and academia. In this study, we strive to create automated systems that can detect machine-generated texts and pinpoint potential misuse. We first introduce a large-scale benchmark \textbf{M4}, which is a multi-generator, multi-domain, and multi-lingual corpus for machine-generated text detection. Through an extensive empirical study of this dataset, we show that it is challenging for detectors to generalize well on instances from unseen domains or LLMs. In such cases, detectors tend to misclassify machine-generated text as human-written. These results show that the problem is far from solved and that there is a lot of room for improvement. We believe that our dataset will enable future research towards more robust approaches to this pressing societal problem. The dataset is available at https://github.com/mbzuai-nlp/M4.