Prasanna Sattigeri

large language model (7) uncertainty quantification (5) transfer learning (3) causal bandit (2) pretrained model (2) intervention target (2) value alignment (2) precision matrix (2) out-of-distribution detection (2) generative adversarial network (2) image classification (2) causal discovery (2) explainable ai (2) human-ai interaction (2) model interpretability (2) structural equation model (2) causal inference (2) mutual information (2) weakly supervised learning (2) hallucination detection (2)