Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
Human-AI hybrids achieve only +0.4pp over AI alone on diverse tasks because confidence routing fails to identify the small set of cases where humans can correct AI errors.
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.
citing papers explorer
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.