← Search

Joseph Enguehard

2 accepted papers

2023

Sequential Integrated Gradients: a simple but effective method for explaining language models

ACL 2023findings

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these methods produce a path for each word of a sentence simultaneously,…