Bryan Wilder

Online Decision Making with Generative Action Sets

LLMs Struggle to Balance Reasoning and World Knowledge in Causal Narrative Understanding

Improving constraint-based discovery with robust propagation and reliable LLM priors

Explaining Concept Shift with Interpretable Feature Attribution

Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning?

Distributionally Robust Feature Selection

Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification

Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources

Reinforcement learning with combinatorial actions for coupled restless bandits

Valid Inference with Imperfect Synthetic Data

Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects

Failure Modes of LLMs for Causal Reasoning on Narratives