Fazl Barez

large language model (6) model editing (3) ai safety (2) neural network interpretability (2) mechanistic interpretability (2) transformer architecture (2) knowledge editing (1) attention mechanism (1) benchmark evaluation (1) model evaluation (1) code generation (1) model safety (1) prompt engineering (1) embedding space (1) reinforcement learning from human feedback (1) kl divergence (1) model interpretability (1) adversarial perturbation (1) language model (1) factual accuracy (1)