Ilya Lasy

hallucination detection (2) natural language generation (2) ensemble method (2) mechanistic interpretability (1) circuit discovery (1) bert fine-tuning (1) large language model (1) verbatim memorization (1) transformer circuit (1) model-agnostic detection (1) model-aware detection (1) transfer learning (1) model-agnostic method (1) bert model (1) language model (1)