TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PromCSE-RoBERTa-large (0.355B)

PromCSE-RoBERTa-large (0.355B)

Reported on 7 benchmarks across 1 task · 1 paper · 4 SOTA

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

Natural Language Processing7 results

  • Semantic Textual SimilarityonSTS14
    Spearman Correlation· 2022-03-14
    0.8381
    best: 0.8689 (AnglE-LLaMA-13B)
    SOTA
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875
  • Semantic Textual SimilarityonSICK
    Spearman Correlation· 2022-03-14
    0.8243
    SOTA
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875
  • Semantic Textual SimilarityonSTS13
    Spearman Correlation· 2022-03-14
    0.8897
    best: 0.9058 (AnglE-LLaMA-7B)
    SOTA
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875
  • Semantic Textual SimilarityonSTS12
    Spearman Correlation· 2022-03-14
    0.7956
    best: 0.802 (PromptEOL+CSE+OPT-13B)
    SOTA
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875
  • Semantic Textual SimilarityonSTS15
    Spearman Correlation· 2022-03-14
    0.8808
    best: 0.9004 (PromptEOL+CSE+LLaMA-30B)
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875
  • Semantic Textual SimilarityonSTS Benchmark
    Spearman Correlation· 2022-03-14
    0.8787
    best: 0.931 (Mnet-Sim)
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875
  • Semantic Textual SimilarityonSTS16
    Spearman Correlation· 2022-03-14
    0.8496
    best: 0.87 (AnglE-LLaMA-7B-v2)
    Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningarXiv:2203.06875