Juhyun Oh

large language model (4) preference alignment (1) text generation (1) offensive language detection (1) bias detection (1) bert model (1) instruction following (1) evaluation framework (1) evaluation benchmark (1) human-ai interaction (1) korean language (1) error classification (1) open-ended generation (1) fine-grained evaluation (1) cultural alignment (1) persona consistency (1) participatory design (1) span detection (1) human-model alignment (1) offensive span detection (1)