GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers Paper • 2205.03286 • Published May 6, 2022
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning Paper • 2211.05610 • Published Nov 10, 2022
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition Paper • 2306.02873 • Published Jun 5, 2023 • 1
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages Paper • 2203.14139 • Published Mar 26, 2022 • 1
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations Paper • 2109.05958 • Published Sep 13, 2021