explainable ai
Explainable AI refers to methods and techniques in artificial intelligence that make the operations and decisions of AI models understandable to humans, enabling users to comprehend how a model arrives at its predictions and fostering trust and accountability in AI systems.
- Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction
- Minimizing False-Positive Attributions in Explanations of Non-Linear Models
- On Logic-based Self-Explainable Graph Neural Networks
- Provable Gradient Editing of Deep Neural Networks
- Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
- Representational Difference Explanations
- SHAP values via sparse Fourier representation
- Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations