Pith. sign in

Saurous, Rif , booktitle =

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

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Learning Latent Reasoning Traces for Scalar Reward Models End-to-End

cs.CL · 2026-07-31 · conditional · novelty 6.0

LatentRM treats reasoning traces as discrete latent variables and trains a generator end-to-end so that the scalar reward model's likelihood of the true preference ranking is maximized, outperforming scalar, generative, and hybrid reward models on average.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Latent Reasoning Traces for Scalar Reward Models End-to-End cs.CL · 2026-07-31 · conditional · none · ref 21

    LatentRM treats reasoning traces as discrete latent variables and trains a generator end-to-end so that the scalar reward model's likelihood of the true preference ranking is maximized, outperforming scalar, generative, and hybrid reward models on average.