Incremental XAI: Memorable Understanding of AI with Incremental Explanations
This work addresses the usability of XAI for users by making explanations more memorable and understandable, though it is incremental in nature.
The paper tackles the problem of users struggling with inaccurate global or highly-varying local explanations in explainable AI (XAI) by proposing Incremental XAI, which provides base and incremental factors to improve memorability and faithfulness, resulting in enhanced user understanding in studies.
Many explainable AI (XAI) techniques strive for interpretability by providing concise salient information, such as sparse linear factors. However, users either only see inaccurate global explanations, or highly-varying local explanations. We propose to provide more detailed explanations by leveraging the human cognitive capacity to accumulate knowledge by incrementally receiving more details. Focusing on linear factor explanations (factors $\times$ values = outcome), we introduce Incremental XAI to automatically partition explanations for general and atypical instances by providing Base + Incremental factors to help users read and remember more faithful explanations. Memorability is improved by reusing base factors and reducing the number of factors shown in atypical cases. In modeling, formative, and summative user studies, we evaluated the faithfulness, memorability and understandability of Incremental XAI against baseline explanation methods. This work contributes towards more usable explanation that users can better ingrain to facilitate intuitive engagement with AI.