← Search

Jonathan Kamp

2 accepted papers

2024

The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement

COLING 2024main

Post-hoc explanation methods are an important tool for increasing model transparency for users. Unfortunately, the currently used methods for attributing token importance often yield diverging patterns. In this work, we study potential sources of disagreement across methods from a linguistic perspec…

2023

Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods

EMNLP 2023short main

Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should be displayed from sequential properties of the attribution scores. Our approach…

Cited by 0SourceScholar