Anchor-guided variance-aware reward modeling uses two response-level anchors to resolve non-identifiability in Gaussian models of pluralistic preferences, yielding provable identification, a joint training objective, and improved RLHF performance.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A recursive Riesz representer-based targeted minimum loss estimation procedure unifies asymptotically efficient estimation of causal estimands such as time-varying treatment effects and mediation effects.
citing papers explorer
-
Variance-aware Reward Modeling with Anchor Guidance
Anchor-guided variance-aware reward modeling uses two response-level anchors to resolve non-identifiability in Gaussian models of pluralistic preferences, yielding provable identification, a joint training objective, and improved RLHF performance.
-
A Riesz Representer Perspective on Targeted Learning
A recursive Riesz representer-based targeted minimum loss estimation procedure unifies asymptotically efficient estimation of causal estimands such as time-varying treatment effects and mediation effects.