AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations

TL;DR

AIDE is a novel explanation method that provides diverse, intent-based, contrastive examples to interpret, investigate, or clarify predictions of complex models, enhancing understanding from multiple perspectives.

Contribution

AIDE introduces a customizable, diversity-aware sampling approach for generating contrastive, intent-specific explanations, addressing limitations of existing homogeneous explanation methods.

Findings

AIDE improves explanation diversity and coverage.

AIDE outperforms existing methods in correctness and user satisfaction.

User study confirms AIDE's effectiveness in real-world tasks.

Abstract

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set of explanation samples, failing to reveal the model's reasoning from different angles. In this paper, we propose AIDE, an approach for providing antithetical (i.e., contrastive), intent-based, diverse explanations for opaque and complex models. AIDE distinguishes three types of explainability intents: interpreting a correct, investigating a wrong, and clarifying an ambiguous prediction. For each intent, AIDE selects an appropriate set of influential training samples that support or oppose the prediction either directly or by contrast. To provide a succinct summary, AIDE uses diversity-aware sampling to avoid redundancy and increase coverage of the training data. We demonstrate the effectiveness of AIDE on image and text classification tasks, in three ways: quantitatively, assessing correctness and continuity; qualitatively, comparing anecdotal evidence from AIDE and other example-based approaches; and via a user study, evaluating multiple aspects of AIDE. The results show that AIDE addresses the limitations of existing methods and exhibits desirable traits for an explainability method.