SelectiveRM applies optimal transport with a joint consistency discrepancy and partial mass relaxation to produce reward models that optimize a tighter upper bound on clean risk while autonomously dropping noisy preference samples.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
The authors propose creating data probes—synthetic sequences from defined random processes—to reveal how data properties drive LLM behavior across workflow stages.
citing papers explorer
-
Optimal Transport for LLM Reward Modeling from Noisy Preference
SelectiveRM applies optimal transport with a joint consistency discrepancy and partial mass relaxation to produce reward models that optimize a tighter upper bound on clean risk while autonomously dropping noisy preference samples.
-
Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance
The authors propose creating data probes—synthetic sequences from defined random processes—to reveal how data properties drive LLM behavior across workflow stages.