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

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Aligning LLMs with Domain Invariant Reward Models

cs.LG · 2025-01-01 · conditional · novelty 4.0

Applying Wasserstein-distance domain adaptation, a known technique, to reward models lets preference signals learned on labeled source data transfer to unlabeled target domains, with consistent but modest gains across four settings.

citing papers explorer

Showing 1 of 1 citing paper.

  • Aligning LLMs with Domain Invariant Reward Models cs.LG · 2025-01-01 · conditional · none · ref 8

    Applying Wasserstein-distance domain adaptation, a known technique, to reward models lets preference signals learned on labeled source data transfer to unlabeled target domains, with consistent but modest gains across four settings.