Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Reward Modeling with Ordinal Feedback: Wisdom of the Crowd

cs.LG · 2024-11-19 · conditional · novelty 6.0

The paper generalizes Bradley-Terry reward modeling to ordinal feedback labels and proves that, under a marginal unbiasedness assumption, finer-grained labels reduce Rademacher complexity and can improve reward learning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Reward Modeling with Ordinal Feedback: Wisdom of the Crowd cs.LG · 2024-11-19 · conditional · none · ref 7

    The paper generalizes Bradley-Terry reward modeling to ordinal feedback labels and proves that, under a marginal unbiasedness assumption, finer-grained labels reduce Rademacher complexity and can improve reward learning.