UDIG is an attribution algorithm that chooses uniform, vocabulary-near interpolation points between a MASK baseline and an input token, improving three faithfulness metrics over Integrated Gradients and Discretized Integrated Gradients on BERT and DistilBERT.
Language models are unsupervised multitask learners.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language models
UDIG is an attribution algorithm that chooses uniform, vocabulary-near interpolation points between a MASK baseline and an input token, improving three faithfulness metrics over Integrated Gradients and Discretized Integrated Gradients on BERT and DistilBERT.