PEBS applies Morris-James-Stein empirical-Bayes shrinkage to per-rater affine calibrators in RLHF, cutting within-user held-out RMSE by 8.58% on PRISM and 9.66% on PluriHarms versus pooled baselines.
2309.00779 , archiveprefix =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
other 1polarities
unclear 1representative citing papers
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
AI value alignment is reconceptualized as a pluralistic governance problem arising along three axes—objectives, information, and principals—making it inherently context-dependent and unsolvable by technical design alone.
citing papers explorer
-
PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration
PEBS applies Morris-James-Stein empirical-Bayes shrinkage to per-rater affine calibrators in RLHF, cutting within-user held-out RMSE by 8.58% on PRISM and 9.66% on PluriHarms versus pooled baselines.
-
Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
AI value alignment is reconceptualized as a pluralistic governance problem arising along three axes—objectives, information, and principals—making it inherently context-dependent and unsolvable by technical design alone.