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

2026 1

verdicts

REJECT 1

representative citing papers

Procedural Fairness Failures in RLHF from Preference Averaging

cs.LG · 2026-08-10 · reject · novelty 3.0

In a synthetic preference-learning setup, PA-RLHF is reported to beat a single averaged reward model on group-level alignment, but the experiment appears to use ground-truth group labels to select the reward model, undermining the comparison.

citing papers explorer

Showing 1 of 1 citing paper.

  • Procedural Fairness Failures in RLHF from Preference Averaging cs.LG · 2026-08-10 · reject · none · ref 7

    In a synthetic preference-learning setup, PA-RLHF is reported to beat a single averaged reward model on group-level alignment, but the experiment appears to use ground-truth group labels to select the reward model, undermining the comparison.