PA-LRP extends Layer-wise Relevance Propagation to attribute relevance to positional encodings in Transformers, improving faithfulness of explanations.
Video and text matching with conditioned embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
PA-LRP extends Layer-wise Relevance Propagation to attribute relevance to positional encodings in Transformers, improving faithfulness of explanations.