MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark

Dominik Macko, Robert Moro, Adaku Uchendu, Jason S Lucas, Michiharu Yamashita, Matúš Pikuliak, Ivan Srba, Thai Le, Dongwon Lee, Jakub Simko, Maria Bielikova

Submission Type: Regular Long Paper

Submission Track: Natural Language Generation

Submission Track 2: Resources and Evaluation

Keywords: text generation, large language models, multilinguality, machine-generated text detection, benchmark

TL;DR: We introduce a benchmark of a wide range of machine-generated text detection methods showing their performance on a novel dataset of 11 languages generated by 8 LLMs.

Abstract: There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual settings. This is also reflected in the available benchmarks which lack authentic texts in languages other than English and predominantly cover older generators. To fill this gap, we introduce MULTITuDE, a novel benchmarking dataset for multilingual machine-generated text detection comprising of 74,081 authentic and machine-generated texts in 11 languages (ar, ca, cs, de, en, es, nl, pt, ru, uk, and zh) generated by 8 multilingual LLMs. Using this benchmark, we compare the performance of zero-shot (statistical and black-box) and fine-tuned detectors. Considering the multilinguality, we evaluate 1) how these detectors generalize to unseen languages (linguistically similar as well as dissimilar) and unseen LLMs and 2) whether the detectors improve their performance when trained on multiple languages.

Submission Number: 1298