interpretation faithfulness

Improving Interpretation Faithfulness for Transformers

Di Wang, Assistant Professor, Computer Science

Nov 20, 11:30 - 12:30

B9 L2 H2 H2

transformers nlp interpretation faithfulness

Currently, attention mechanism becomes a standard fixture in most state-of-the-art NLP, Vision and GNN models, not only due to outstanding performance it could gain, but also due to plausible innate explanation for the behaviors of neural architectures it provides, which is notoriously difficult to analyze. However, recent studies show that attention is unstable against randomness and perturbations during training or testing, such as random seeds and slight perturbation of input or embedding vectors, which impedes it from becoming a faithful explanation tool. Thus, a natural question is whether we can find some substitute of the current attention which is more stable and could keep the most important characteristics on explanation and prediction of attention.