Skip to content
conftrace_

constitutional alignment

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

iterative fine-tuning (1) dialogue system (1) self-supervised alignment (1) constitutional ai (1) constitutional principle (1) preference label (1) language model (1) preference modeling (1) mutual information (1) language model alignment (1)

Papers

Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels NeurIPS 2024