MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
This addresses the problem of detecting AI-generated text in non-English languages for researchers and practitioners, though it is incremental as it extends existing benchmarking efforts to multilingual settings.
The authors tackled the lack of multilingual benchmarks for machine-generated text detection by introducing MULTITuDE, a dataset with 74,081 texts in 11 languages from 8 LLMs, and found that detectors show varied generalization to unseen languages and LLMs, with performance improvements when trained on multiple languages.
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.