[2403.10415] Gradient based Feature Attribution in Explainable AI: A Technical Review

The surge in black-box AI models has prompted the need to explain the internal mechanism and justify their reliability, especially in high-stakes applications, such as healthcare and autonomous driving. Due to the lack…

Gradient based Feature Attribution in Explainable AI: A Technical Review Yongjie Wang Nanyang technological university yongjie002@e.ntu.edu.sg , Tong Zhang Nanyang technological university tong.zhang@ntu.edu.sg , Xu Guo Nanyang technological university xu.guo@ntu.edu.sg and Zhiqi Shen Nanyang technological university zqshen@ntu.edu.sg (2024) Abstract. The surge in black-box AI models has prompted the need to explain the internal mechanism and justify their reliability, especially in high-stakes applications, such as healthcare and autonomous driving. Due to the lack of a rigorous definition of

related reading

• The Building Blocks of Interpretabilitydistill.pub
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• 2404.17625arxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• 2310.01405.pdfarxiv.org
• 2310.01405arxiv.org
• [1706.04599] On Calibration of Modern Neural Networksarxiv.org
• Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelsarxiv.org
• Prediction, Explanation, or Over-interpretation?elena-baixy.github.io
• 2410.04332arxiv.org
• Understanding deep learning requires rethinking generalizationarxiv.org