activity
20242026
collaborators

7 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…

cs.CR2026

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models

Pang Liu, Yingjie Lao

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is…

stat.ML2026

Reinforcement Learning from Human Feedback: A Statistical Perspective

Pangpang Liu, Chengchun Shi, Will Wei Sun

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success…

cs.GT2026

Fairness-aware Contextual Dynamic Pricing with Strategic Buyers

Pangpang Liu, Will Wei Sun

Contextual pricing strategies are prevalent in online retailing, where the seller adjusts prices based on products' attributes and buyers' characteristics. Although such strategies…

stat.ML2025

Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback

Pangpang Liu, Junwei Lu, Will Wei Sun

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human…