HC-RLHF returns an aligned language model only after a held-out safety test certifies, with probability at least 1-delta, that expected harm (as judged by a learned cost model) is below a chosen threshold.
Rank analysis of incomplete block designs: I
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
HC-RLHF returns an aligned language model only after a held-out safety test certifies, with probability at least 1-delta, that expected harm (as judged by a learned cost model) is below a chosen threshold.