Provide Contextual Information

AI Model
Ensemble Neural Network None Probabilistic Unknown
AI Task
Binary classification Embedding Multi-class Classification
Application Domain
Health Network
Type of Users
AI experts Domain-experts Non-experts
Explanation Modality
Natural Language Text Visual
XAI Model
Counter-exemplars/factual Decision Rules Exemplars Features Importance Neurons Activation Salient Mask Sensitivity Analysis Shapley Values
Related Papers

Placing explanations together with additional contextual information enhances their relevance and interpretability to domain-expert users, e.g., physicians [10.1109/TVCG.2021.3114836,10.2196/28659], AI engineers [10.1145/3613904.3642106,10.1109/VAST50239.2020.00010], etc. Moreover, the depth of information in explanations should be adaptable to the user’s expertise, ensuring that both detailed and summary information are available without overwhelming the user [10.1007/978-3-031-60606-9_13, 10.1016/j.ijhcs.2022.102941, 10.1145/3290605.3300831]