Explainable AI
A field of AI research dedicated to making the decision-making processes of AI systems understandable and interpretable to humans. Commonly used techniques include post-hoc explanation methods such as LIME and SHAP, which are approximations and cannot provide complete causal chains.
Timeline (last 90 days)
In scientific research, if researchers cannot explain why a black-box model made a certain prediction, they cannot judge whether that prediction is based on a reasonable mechanism or fits a spurious correlation.
Mainstream explainable AI techniques include post-hoc explanation methods such as SHAP (game-theory-based Shapley value attribution), LIME (local interpretable model-agnostic explanations), and attention mechanism visualization, as well as inherently interpretable models such as decision trees, logistic regression, and rule lists.
All Facts (2)
In scientific research, if researchers cannot explain why a black-box model made a certain prediction, they cannot judge whether that prediction is based on a reasonable mechanism or fits a spurious correlation.
50%UnverifiedMainstream explainable AI techniques include post-hoc explanation methods such as SHAP (game-theory-based Shapley value attribution), LIME (local interpretable model-agnostic explanations), and attention mechanism visualization, as well as inherently interpretable models such as decision trees, logistic regression, and rule lists.
50%