conftrace_

ipo

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

ipo-md (1) online policy (1) slic (1) dpo (1) alignment (1) offline alignment (1) preference model (1) convex function (1) nash equilibrium (1) preference optimization (1)

Papers

Generalized Preference Optimization: A Unified Approach to Offline Alignment ICML 2024 Human Alignment of Large Language Models through Online Preference Optimisation ICML 2024