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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society, AIES 2024 |
| Editors | Sanmay Das, Brian Patrick Green, Kush Varshney, Marianna Ganapini, Andrea Renda |
| Publisher | AAAI Press |
| Pages | 1051-1062 |
| Number of pages | 12 |
| ISBN (Electronic) | 1577358929, 9781577358923 |
| DOIs | |
| State | Published - 2024 |
| Externally published | Yes |
| Event | 7th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2024 - San Jose, United States Duration: 21 Oct 2024 → 23 Oct 2024 |
Publication series
| Name | Proceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society, AIES 2024 |
|---|
Conference
| Conference | 7th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2024 |
|---|---|
| Country/Territory | United States |
| City | San Jose |
| Period | 21/10/24 → 23/10/24 |
Bibliographical note
Publisher Copyright:Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
ASJC Scopus subject areas
- Artificial Intelligence
Fingerprint
Dive into the research topics of 'AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver