By combining CLIP-based cross-modal alignment with ranking distillation from SimCSE and DiffCSE teachers, DALR improves average STS scores by about 0.8 to 1.0 points over KDMCSE across BERT and RoBERTa.
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
-
DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning
By combining CLIP-based cross-modal alignment with ranking distillation from SimCSE and DiffCSE teachers, DALR improves average STS scores by about 0.8 to 1.0 points over KDMCSE across BERT and RoBERTa.