TELL is a new architecture for AI text detection that natively supplies explanatory annotations, reaching AUROC 0.927 and a 72.3% human win-rate on explanation quality metrics.
InFindings of the Association for Computational Linguistics: EMNLP 2023, pages 12395–12412
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MGTEVAL is an extensible platform that unifies dataset construction, attack application, detector training, and performance reporting for machine-generated text detectors.
citing papers explorer
-
Show, Don't TELL: Explainable AI-Generated Text Detection
TELL is a new architecture for AI text detection that natively supplies explanatory annotations, reaching AUROC 0.927 and a 72.3% human win-rate on explanation quality metrics.