| Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning | ✓ Link | 0.8243 | PromCSE-RoBERTa-large (0.355B) | 2022-03-14 |
| Scaling Sentence Embeddings with Large Language Models | ✓ Link | 0.8238 | PromptEOL+CSE+LLaMA-30B | 2023-07-31 |
| Scaling Sentence Embeddings with Large Language Models | ✓ Link | 0.8206 | PromptEOL+CSE+OPT-13B | 2023-07-31 |
| SimCSE: Simple Contrastive Learning of Sentence Embeddings | ✓ Link | 0.8195 | SimCSE-RoBERTalarge | 2021-04-18 |
| Scaling Sentence Embeddings with Large Language Models | ✓ Link | 0.8129 | PromptEOL+CSE+OPT-2.7B | 2023-07-31 |
| Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks | ✓ Link | 0.7462 | SentenceBERT | 2019-08-27 |
| Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks | ✓ Link | 0.7446 | SRoBERTa-NLI-base | 2019-08-27 |
| Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks | ✓ Link | 0.7429 | SRoBERTa-NLI-large | 2019-08-27 |
| Generating Datasets with Pretrained Language Models | ✓ Link | 0.7426 | Dino (STS/̄🦕) | 2021-04-15 |
| Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks | ✓ Link | 0.7375 | SBERT-NLI-large | 2019-08-27 |
| Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks | ✓ Link | 0.7291 | SBERT-NLI-base | 2019-08-27 |
| Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations | ✓ Link | 0.7276 | Trans-Encoder-BERT-base-bi (unsup.) | 2021-09-27 |
| Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations | ✓ Link | 0.7192 | Trans-Encoder-BERT-large-cross (unsup.) | 2021-09-27 |
| Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations | ✓ Link | 0.7163 | Trans-Encoder-RoBERTa-large-cross (unsup.) | 2021-09-27 |
| Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations | ✓ Link | 0.7133 | Trans-Encoder-BERT-large-bi (unsup.) | 2021-09-27 |
| Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders | ✓ Link | 0.706 | Mirror-RoBERTa-base (unsup.) | 2021-04-16 |
| Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders | ✓ Link | 0.703 | Mirror-BERT-base (unsup.) | 2021-04-16 |
| Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations | ✓ Link | 0.6952 | Trans-Encoder-BERT-base-cross (unsup.) | 2021-09-27 |
| Generating Datasets with Pretrained Language Models | ✓ Link | 0.6809 | Dino (STSb/̄🦕) | 2021-04-15 |
| Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity | ✓ Link | 0.6772 | Rematch | 2024-04-02 |
| On the Sentence Embeddings from Pre-trained Language Models | ✓ Link | 0.6544 | BERTbase-flow (NLI) | 2020-11-02 |
| An Unsupervised Sentence Embedding Method by Mutual Information Maximization | ✓ Link | 0.6425 | IS-BERT-NLI | 2020-09-25 |