DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
This addresses the problem of inconsistent and unverifiable explanations in AI for users needing reliable interpretability, though it is incremental as it builds on existing faithfulness metrics and methods.
The paper tackles the lack of a unified ground truth for evaluating and optimizing explainable AI methods by proposing DeepFaith, a domain-free and model-agnostic framework that achieves optimal faithfulness across multiple metrics, resulting in the highest overall faithfulness on 12 diverse tasks compared to baselines.
Explainable AI (XAI) builds trust in complex systems through model attribution methods that reveal the decision rationale. However, due to the absence of a unified optimal explanation, existing XAI methods lack a ground truth for objective evaluation and optimization. To address this issue, we propose Deep architecture-based Faith explainer (DeepFaith), a domain-free and model-agnostic unified explanation framework under the lens of faithfulness. By establishing a unified formulation for multiple widely used and well-validated faithfulness metrics, we derive an optimal explanation objective whose solution simultaneously achieves optimal faithfulness across these metrics, thereby providing a ground truth from a theoretical perspective. We design an explainer learning framework that leverages multiple existing explanation methods, applies deduplicating and filtering to construct high-quality supervised explanation signals, and optimizes both pattern consistency loss and local correlation to train a faithful explainer. Once trained, DeepFaith can generate highly faithful explanations through a single forward pass without accessing the model being explained. On 12 diverse explanation tasks spanning 6 models and 6 datasets, DeepFaith achieves the highest overall faithfulness across 10 metrics compared to all baseline methods, highlighting its effectiveness and cross-domain generalizability.