pith. sign in

InThe Thirty-eighth Annual Conference on Neural Information Processing Systems

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

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences

cs.CL · 2026-04-15 · unverdicted · novelty 6.0

C2 synthesizes contrastive helpful/misleading rubric pairs from binary preferences to train cooperative generators and critical verifiers, yielding up to 6.5-point gains on RM-Bench and enabling smaller models to match larger rubric-augmented ones.

citing papers explorer

Showing 1 of 1 citing paper.

  • C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences cs.CL · 2026-04-15 · unverdicted · none · ref 6

    C2 synthesizes contrastive helpful/misleading rubric pairs from binary preferences to train cooperative generators and critical verifiers, yielding up to 6.5-point gains on RM-Bench and enabling smaller models to match larger rubric-augmented ones.