William Held

dialect adaptation (3) large language model (3) transfer learning (3) semantic parsing (2) user preference (2) zero-shot learning (2) spoken question answering (2) data augmentation (1) reward modeling (1) contrastive learning (1) knowledge distillation (1) machine translation (1) self-supervised learning (1) speech recognition (1) direct preference optimization (1) benchmark evaluation (1) information retrieval (1) preference learning (1) toxicity detection (1) prompt engineering (1)