cd/entity/GlobalOpinionQA· home› entities› GlobalOpinionQA
grep -l @globalopinionqa /news/*.json | wc -l → 1

GlobalOpinionQA

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

04:00
2026-06-18
arxiv.org
large-language-models

Steerable Cultural Preference Optimization of Reward Models

Researchers introduced Steerable Cultural Preference Optimization (SCPO), a reward model training algorithm that balances diverse cultural preferences in large language models. SCPO improved minority …

// co-occurs with top 4 entities
SCPO 1 PRISM 1 arXiv 1 GitHub 1
// topics top 4 topics
large language models 1 ai ethics 1 ai research 1 machine learning 1