Fanny Jourdan

concept-based explanation (3) transformer model (2) interpretable machine learning (1) explainable ai (1) model interpretability (1) sensitivity analysis (1) machine learning (1) fairness metric (1) group fairness (1) non-negative matrix factorization (1) attribution method (1) gender bia (1) explanation evaluation (1) automated simulatability (1) explanation quality (1) concept space (1) large language model (1) occupation prediction (1) bias assessment (1) sentiment analysis (1)