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
Are Linear Regression Models White Box and Interpretable?
Ahmed M Salih, Yuhe Wang
XTraffic: A Dataset Where Traffic Meets Incidents with Explainability and More
Xiaochuan Gou, Ziyue Li, Tian Lan, Junpeng Lin, Zhishuai Li, Bingyu Zhao, Chen Zhang, Di Wang, Xiangliang Zhang
SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks
Zhenhua Huang, Kunhao Li, Shaojie Wang, Zhaohong Jia, Wentao Zhu, Sharad Mehrotra