How Reliable and Stable are Explanations of XAI Methods?

Documenti analoghi

• Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
  di: Ribeiro, José, et al.
  Pubblicazione: (2022)
• Explanations Based on Item Response Theory (eXirt): A Model-Specific Method to Explain Tree-Ensemble Model in Trust Perspective
  di: Ribeiro, José, et al.
  Pubblicazione: (2022)
• Enhancing Classifier Evaluation: A Fairer Benchmarking Strategy Based on Ability and Robustness
  di: Cardoso, Lucas, et al.
  Pubblicazione: (2025)
• Beyond Random Sampling: Instance Quality-Based Data Partitioning via Item Response Theory
  di: Cardoso, Lucas, et al.
  Pubblicazione: (2025)
• Standing on the shoulders of giants
  di: Cardoso, Lucas Felipe Ferraro, et al.
  Pubblicazione: (2024)