CURE removes concept-level spurious correlations from pre-trained embeddings via a content extractor, a reversal network, and a margin-controlled contrastive module, improving OOD sentiment F1 by up to 10 points on IMDB and about 2 points on Yelp.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
CURE removes concept-level spurious correlations from pre-trained embeddings via a content extractor, a reversal network, and a margin-controlled contrastive module, improving OOD sentiment F1 by up to 10 points on IMDB and about 2 points on Yelp.