SimCSE-RoBERTa-large

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Semantic Textual SimilarityonSTS13
Spearman Correlation· 2021-04-18
0.8727
best: 0.9058 (AnglE-LLaMA-7B)
SOTA
SimCSE: Simple Contrastive Learning of Sentence Embeddings arXiv:2104.08821
Semantic Textual SimilarityonSTS12
Spearman Correlation· 2021-04-18
0.7746
best: 0.802 (PromptEOL+CSE+OPT-13B)
SOTA
SimCSE: Simple Contrastive Learning of Sentence Embeddings arXiv:2104.08821