Local calibration of likelihood ratios conditioned on hidden-space position corrects Simpson's paradox in token averaging and substantially improves machine-text detection across baselines.
RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns.Transactions of the Association for Computational Linguistics, 13:1812–1831, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
Local calibration of likelihood ratios conditioned on hidden-space position corrects Simpson's paradox in token averaging and substantially improves machine-text detection across baselines.