A Shapley-value-based counterfactual regularization improves dense retrievers' robustness to adversarial attacks and enables key passage extraction without passage-level relevance annotations.
2008.Models in cooperative game theory
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.IR 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unsupervised dense retrieval with conterfactual contrastive learning
A Shapley-value-based counterfactual regularization improves dense retrievers' robustness to adversarial attacks and enables key passage extraction without passage-level relevance annotations.