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
Directly Handling Missing Data in Linear Discriminant Analysis for Enhancing Classification Accuracy and Interpretability
Tuan L. Vo, Uyen Dang, Thu Nguyen
HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability
Yanfang Chen, Ding Chen, Shichao Song, Simin Niu, Hanyu Wang, Zeyun Tang, Feiyu Xiong, Zhiyu Li