#preference-learning2 articles

2 articles

AIBullisharXiv – CS AI · 5h ago1

🧠

Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals

Researchers introduce Density-Guided Response Optimization (DGRO), a new AI alignment method that learns community preferences from implicit acceptance signals rather than explicit feedback. The technique uses geometric patterns in how communities naturally engage with content to train language models without requiring costly annotation or preference labeling.

AIBullisharXiv – CS AI · 5h ago0

🧠

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

Researchers introduce Skywork-Reward-V2, a suite of AI reward models trained on SynPref-40M, a massive 40-million preference pair dataset created through human-AI collaboration. The models achieve state-of-the-art performance across seven major benchmarks by combining human annotation quality with AI scalability for better preference learning.