Контрастты түсіндірулер
method
ID: contrastiveexplanations
Related Papers
Aligning Faithful Interpretations with their Social Attribution
AbstractWe find that the requirement of model interpretations to be faithful is vague and incomplete. With interpretation by textual highlights as a case study, we present several failure cases. Borrowing …...
Contrastive Explanations for Model Interpretability
AbstractContrastive explanations clarify why an event occurred in contrast to another. They are inherently intuitive to humans to both produce and comprehend. We propose a method to produce contrastive explanations …...
Interpreting Language Models with Contrastive Explanations
AbstractModel interpretability methods are often used to explain NLP model decisions on tasks such as text classification, where the output space is relatively small. However, when applied to language generation, …...