High Explainability
High explainability in artificial intelligence (AI) aims to make the decision-making processes of complex models, such as large language models and deep neural networks, more transparent and understandable. Current research focuses on developing both intrinsic (built-in) and post-hoc (added after training) explainability methods, often employing techniques like attention mechanisms, feature attribution, and counterfactual examples to interpret model outputs across various modalities (text, images, audio). This pursuit is crucial for building trust in AI systems, particularly in high-stakes domains like medicine and finance, and for ensuring fairness, accountability, and responsible AI development.
Papers
Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections
Armin Kirchknopf, Djordje Slijepcevic, Ilkay Wunderlich, Michael Breiter, Johannes Traxler, Matthias Zeppelzauer
Explainability of Traditional and Deep Learning Models on Longitudinal Healthcare Records
Lin Lee Cheong, Tesfagabir Meharizghi, Wynona Black, Yang Guang, Weilin Meng
Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement
Montgomery Flora, Corey Potvin, Amy McGovern, Shawn Handler
Using explainability to design physics-aware CNNs for solving subsurface inverse problems
Jodie Crocker, Krishna Kumar, Brady R. Cox