pith. machine review for the scientific record. sign in

Reward-free alignment for conflicting objectives

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

RVPO: Risk-Sensitive Alignment via Variance Regularization

cs.LG · 2026-05-07 · unverdicted · novelty 6.0

RVPO penalizes variance across multiple reward signals during RLHF advantage aggregation, using a LogSumExp operator as a smooth variance penalty to reduce constraint neglect in LLM alignment.

citing papers explorer

Showing 2 of 2 citing papers.