SOLiD scales to 405B models with undetected deception dropping to 14% at 99% TPR, permits removing human labelers from fine-tuning without significant deception increase, but fails under distribution shift.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scaling Trends for Lie Detector Oversight in Preference Learning
SOLiD scales to 405B models with undetected deception dropping to 14% at 99% TPR, permits removing human labelers from fine-tuning without significant deception increase, but fails under distribution shift.