Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective
Yongjin Cui, Xiaohui Fan
We observe a phenomenon that current algorithmic research in the field of explainable artificial intelligence primarily pursues better performance on several proxy metrics. On the…
cs.AI2026
Transformer Interpretability from Perspective of Attention and Gradient
Yongjin Cui, Xiaohui Fan, Huajun Chen
Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Tra…