Moninder Singh

model interpretability (2) large language model (2) explainable ai (2) text classification (1) reward function (1) model safety (1) interpretable machine learning (1) inverse reinforcement learning (1) evaluation metric (1) constraint satisfaction (1) decision tree (1) data summarization (1) knowledge graph (1) regret bound (1) contextual bandit (1) feature attribution (1) value alignment (1) model ranking (1) model evaluation (1) anomaly detection (1)