Methods › Natural Language Processing › Sentence Embeddings › SimCSE
SimCSE
Introduced by Tianyu Gao et al. in SimCSE: Simple Contrastive Learning of Sentence Embeddings
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in contrastive objective, with only standard dropout used as noise. The authors find that dropout acts as minimal “data augmentation” of hidden representations, while removing it leads to a representation collapse. Afterwards a supervised approach is used, which incorporates annotated pairs from natural language inference datasets into the contrastive framework, by using “entailment” pairs as positives and “contradiction
Papers archive 2025-07-28
30 shown of 52, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations 15 May 2025 · 1 repository · arXiv:2505.10354
-
Revisiting Word Embeddings in the LLM Era 26 Feb 2025 · 0 repositories · arXiv:2502.19607
-
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls 16 Feb 2025 · 1 repository · arXiv:2502.11183Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings 23 Jan 2025 · 0 repositories · arXiv:2501.13758
-
A Comparative Study of Text Retrieval Models on DaReCzech 19 Nov 2024 · 0 repositories · arXiv:2411.12921
-
HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives 19 Nov 2024 · 0 repositories · arXiv:2411.12156
-
Deep Learning Based Dense Retrieval: A Comparative Study 27 Oct 2024 · 0 repositories · arXiv:2410.20315
-
ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings 28 Aug 2024 · 1 repository · arXiv:2409.00120
-
DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries 25 May 2024 · 1 repository · arXiv:2405.16153
-
Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings 23 Feb 2024 · 0 repositories · arXiv:2402.15153
-
Similarity-based Neighbor Selection for Graph LLMs 6 Feb 2024 · 1 repository · arXiv:2402.03720Syntology ran 6 of 9 samples · 3 unverified · 9 pointer-only (licence)
-
UNSEE: Unsupervised Non-contrastive Sentence Embeddings 27 Jan 2024 · 1 repository · arXiv:2401.15316Syntology ran 2 of 2 samples · 0 unverified
-
Contrastive Learning in Distilled Models 23 Jan 2024 · 1 repository · arXiv:2401.12472
-
GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models 7 Dec 2023 · 1 repository
-
Sparse Contrastive Learning of Sentence Embeddings 7 Nov 2023 · 0 repositories · arXiv:2311.03881
-
Japanese SimCSE Technical Report 30 Oct 2023 · 1 repository · arXiv:2310.19349
-
Non-contrastive sentence representations via self-supervision 26 Oct 2023 · 0 repositories · arXiv:2310.17690
-
Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning 17 Oct 2023 · 1 repository · arXiv:2310.10962
-
Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE 10 Oct 2023 · 1 repository · arXiv:2310.06918
-
SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels 21 Sep 2023 · 0 repositories · arXiv:2309.13080
-
DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective 14 Sep 2023 · 0 repositories · arXiv:2309.07396
-
SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings 21 Jun 2023 · 0 repositories · arXiv:2306.12280
-
CMLM-CSE: Based on Conditional MLM Contrastive Learning for Sentence Embeddings 16 Jun 2023 · 0 repositories · arXiv:2306.09594
-
BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs 6 Jun 2023 · 1 repository · arXiv:2306.03355
-
C-STS: Conditional Semantic Textual Similarity 24 May 2023 · 1 repository · arXiv:2305.15093Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
-
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives 22 May 2023 · 0 repositories · arXiv:2305.13192
-
CSDR-BERT: a pre-trained scientific dataset match model for Chinese Scientific Dataset Retrieval 30 Jan 2023 · 0 repositories · arXiv:2301.12700
-
MED-SE: Medical Entity Definition-based Sentence Embedding 9 Dec 2022 · 0 repositories · arXiv:2212.04734
-
Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches 29 Nov 2022 · 2 repositories · arXiv:2211.16285
-
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings 11 Nov 2022 · 1 repository · arXiv:2211.06127Syntology ran 5 of 10 samples · 5 unverified
Tasks archive 2025-07-28
20 shown of 53 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections