Fanny Jourdan

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