Atticus Geiger

causal abstraction (8) natural language inference (6) causal inference (5) neural network (4) sentiment analysis (4) language model (4) natural language processing (3) concept-based explanation (2) ternary classification (2) neural network interpretability (2) representation learning (2) adversarial testing (2) benchmark dataset (2) distributed representation (2) neural model (2) in-context learning (1) few-shot learning (1) knowledge distillation (1) dataset creation (1) benchmark evaluation (1)