Temperature adjustment on the reference model generalizes inference-time alignment to SLOP ensembles of reward models, with a calibration algorithm that improves robustness to reward hacking while preserving alignment performance.
Regularized best-of-n sampling with minimum bayes risk objective for language model alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
Temperature adjustment on the reference model generalizes inference-time alignment to SLOP ensembles of reward models, with a calibration algorithm that improves robustness to reward hacking while preserving alignment performance.