Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback
The framework thereby makes preference aggregation an explicit and statistically analyzable design choice rather than an implicit consequence of pooling human feedback, and produces a single policy with explicit collective-welfare guarantees.
Hui-Ying Zhong, Tian-Wei Gao, Z. Wu et al.
· 30 citations
· ⚡4