all AI news
Incorporating Attribution Importance for Improving Faithfulness Metrics. (arXiv:2305.10496v1 [cs.CL] CROSS LISTED)
cs.CL updates on arXiv.org arxiv.org
Feature attribution methods (FAs) are popular approaches for providing
insights into the model reasoning process of making predictions. The more
faithful a FA is, the more accurately it reflects which parts of the input are
more important for the prediction. Widely used faithfulness metrics, such as
sufficiency and comprehensiveness use a hard erasure criterion, i.e. entirely
removing or retaining the top most important tokens ranked by a given FA and
observing the changes in predictive likelihood. However, this hard criterion …
arxiv attribution cs.cl feature importance insights making metrics popular prediction predictions process reasoning