SALAD combines POS-tag-masked positives and LLM-generated counterfactual negatives in a contrastive loss to make fine-tuned language models more robust to spurious correlations.
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
-
SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data
SALAD combines POS-tag-masked positives and LLM-generated counterfactual negatives in a contrastive loss to make fine-tuned language models more robust to spurious correlations.