Martín Santillán Cooper

evaluation framework (3) large language model (3) user simulation (2) human evaluation (2) interactive ai (2) quantitative evaluation (2) responsible ai (1) ai safety (1) synthetic data generation (1) human-computer interaction (1) machine learning (1) synthetic datum (1) evaluation metric (1) retrieval-augmented generation (1) token probability (1) hallucination detection (1) harmful content detection (1) error analysis (1) positional bia (1) trustworthy evaluation (1)