A matched four-regime benchmark shows AI-text detectors catch direct LLM output but lose most of their recall on human text rewritten by an LLM.
, author Schlippe, T
1 Pith paper cite this work, alongside 15 external citations. Polarity classification is still indexing.
1
Pith paper citing it
15
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation
A matched four-regime benchmark shows AI-text detectors catch direct LLM output but lose most of their recall on human text rewritten by an LLM.