Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models

Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui Zhang, Xuyang Liu, Weiya Li, Xuming Hu, Linfeng Zhang

Abstract

The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, *AutoGnothi*, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. *AutoGnothi* enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that *AutoGnothi* offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability.
BibTeX
@inproceedings{wang2025gnothi,
  author = {Shaobo Wang and Hongxuan Tang and Mingyang Wang and Hongrui Zhang and Xuyang Liu and Weiya Li and Xuming Hu and Linfeng Zhang},
  title = {{Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models}},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=UvMSKonce8},
}
Figure