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.
Transformers State-of-the-art natural language processing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.