WETBench shows that existing machine-generated text detectors, particularly zero-shot methods, underperform on task-specific Wikipedia editing scenarios, with supervised detectors averaging 78% accuracy and zero-shot detectors 58%.
mDeBERTaV3mDeBERTaV342 is the multilin- gual version of DeBERTa (He et al., 2023), which enhances BERT and RoBERTa using disentangled attention and an improved masked decoder
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia
WETBench shows that existing machine-generated text detectors, particularly zero-shot methods, underperform on task-specific Wikipedia editing scenarios, with supervised detectors averaging 78% accuracy and zero-shot detectors 58%.