3 papers
cs.AI2026
LIBRA: Language Model Informed Bandit Recourse Algorithm for Personalized Treatment Planning
Junyu Cao, Ruijiang Gao, Esmaeil Keyvanshokooh +1
We introduce a unified framework that seamlessly integrates algorithmic recourse, contextual bandits, and large language models (LLMs) to support sequential decision-making in high…
stat.ML2026
Beyond Demand Estimation: Consumer Surplus Evaluation via Cumulative Propensity Weights
Zeyu Bian, Max Biggs, Ruijiang Gao +1
This paper develops a practical framework for using observational data to audit the consumer surplus effects of AI-driven decisions, specifically in targeted pricing and algorithmi…
cs.HC2025
Revealing AI Reasoning Increases Trust but Crowds Out Unique Human Knowledge
Zenan Chen, Ruijiang Gao, Yingzhi Liang
Effective human-AI collaboration requires humans to accurately gauge AI capabilities and calibrate their trust accordingly. Humans often have context-dependent private information,…