2 papers
cs.AI2026
Distributionally Robust Listwise Preference Optimization
Xudong Wu, Jian Qian, Pangpang Liu +2
Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at the dataset, prompt, or preference-pair level. We…
cs.LG2026
On the Convergence of Self-Improving Online LLM Alignment
Xudong Wu, Pangpang Liu, Vaneet Aggarwal +1
The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method. Empirically, SAIL…