cd/entity/PA-RLHF· home› entities› PA-RLHF
grep -l @pa-rlhf /news/*.json | wc -l → 1

PA-RLHF

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

04:00
2026-08-12
arxiv.org
artificial-intelligence

Procedural Fairness Failures in RLHF from Preference Averaging

Researchers from an unnamed institution introduced Preference-Aware RLHF (PA-RLHF), a method that separates optimization across preference modes during reward learning, to address procedural fairness …

// co-occurs with top 1 entities
RLHF 1
// topics top 4 topics
artificial intelligence 1 machine learning 1 ai ethics 1 ai research 1