{"url":"/method/simcse","slug":"simcse","name":"SimCSE","full_name":"SimCSE","full_name_withheld":false,"description_markdown":"**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](https://paperswithcode.com/method/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","description_state":"present","introduced_year":null,"introduced_by":{"title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","paper":"/paper/simcse-simple-contrastive-learning-of","first_author":"Tianyu Gao","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/simcse-simple-contrastive-learning-of"},"source":{"url":"https://arxiv.org/abs/2104.08821v4","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Sentence Embeddings","url":"/methods/category/sentence-embeddings","pwc_aliases":[]}],"n_papers_tagged":52,"archive_num_papers":52,"papers_newest_first":[{"paper":"/paper/ldir-low-dimensional-dense-and-interpretable","title":"LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations","date":"2025-05-15","arxiv_id":"2505.10354","n_code_links":1,"syntology":null},{"paper":null,"title":"Revisiting Word Embeddings in the LLM Era","date":"2025-02-26","arxiv_id":"2502.19607","n_code_links":0,"syntology":null},{"paper":"/paper/don-t-get-lost-in-the-trees-streamlining-llm","title":"Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls","date":"2025-02-16","arxiv_id":"2502.11183","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":null,"title":"2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings","date":"2025-01-23","arxiv_id":"2501.13758","n_code_links":0,"syntology":null},{"paper":null,"title":"A Comparative Study of Text Retrieval Models on DaReCzech","date":"2024-11-19","arxiv_id":"2411.12921","n_code_links":0,"syntology":null},{"paper":null,"title":"HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives","date":"2024-11-19","arxiv_id":"2411.12156","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Learning Based Dense Retrieval: A Comparative Study","date":"2024-10-27","arxiv_id":"2410.20315","n_code_links":0,"syntology":null},{"paper":"/paper/concse-unified-contrastive-learning-and","title":"ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings","date":"2024-08-28","arxiv_id":"2409.00120","n_code_links":1,"syntology":null},{"paper":"/paper/defsent-improving-sentence-embeddings-of","title":"DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries","date":"2024-05-25","arxiv_id":"2405.16153","n_code_links":1,"syntology":null},{"paper":null,"title":"Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings","date":"2024-02-23","arxiv_id":"2402.15153","n_code_links":0,"syntology":null},{"paper":"/paper/similarity-based-neighbor-selection-for-graph","title":"Similarity-based Neighbor Selection for Graph LLMs","date":"2024-02-06","arxiv_id":"2402.03720","n_code_links":1,"syntology":{"ran":6,"of":9,"unverified":3,"pointer_only":9}},{"paper":"/paper/unsee-unsupervised-non-contrastive-sentence","title":"UNSEE: Unsupervised Non-contrastive Sentence Embeddings","date":"2024-01-27","arxiv_id":"2401.15316","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}},{"paper":"/paper/contrastive-learning-in-distilled-models","title":"Contrastive Learning in Distilled Models","date":"2024-01-23","arxiv_id":"2401.12472","n_code_links":1,"syntology":null},{"paper":"/paper/gym-at-quran-qa-2023-shared-task-multi-task","title":"GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models","date":"2023-12-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Sparse Contrastive Learning of Sentence Embeddings","date":"2023-11-07","arxiv_id":"2311.03881","n_code_links":0,"syntology":null},{"paper":"/paper/japanese-simcse-technical-report","title":"Japanese SimCSE Technical Report","date":"2023-10-30","arxiv_id":"2310.19349","n_code_links":1,"syntology":null},{"paper":null,"title":"Non-contrastive sentence representations via self-supervision","date":"2023-10-26","arxiv_id":"2310.17690","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-aware-contrastive-sentence","title":"Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning","date":"2023-10-17","arxiv_id":"2310.10962","n_code_links":1,"syntology":null},{"paper":"/paper/improving-contrastive-learning-of-sentence-2","title":"Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE","date":"2023-10-10","arxiv_id":"2310.06918","n_code_links":1,"syntology":null},{"paper":null,"title":"SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels","date":"2023-09-21","arxiv_id":"2309.13080","n_code_links":0,"syntology":null},{"paper":null,"title":"DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective","date":"2023-09-14","arxiv_id":"2309.07396","n_code_links":0,"syntology":null},{"paper":null,"title":"SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings","date":"2023-06-21","arxiv_id":"2306.12280","n_code_links":0,"syntology":null},{"paper":null,"title":"CMLM-CSE: Based on Conditional MLM Contrastive Learning for Sentence Embeddings","date":"2023-06-16","arxiv_id":"2306.09594","n_code_links":0,"syntology":null},{"paper":"/paper/batchsampler-sampling-mini-batches-for","title":"BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs","date":"2023-06-06","arxiv_id":"2306.03355","n_code_links":1,"syntology":null},{"paper":"/paper/csts-conditional-semantic-textual-similarity","title":"C-STS: Conditional Semantic Textual Similarity","date":"2023-05-24","arxiv_id":"2305.15093","n_code_links":1,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":4}},{"paper":null,"title":"SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives","date":"2023-05-22","arxiv_id":"2305.13192","n_code_links":0,"syntology":null},{"paper":null,"title":"CSDR-BERT: a pre-trained scientific dataset match model for Chinese Scientific Dataset Retrieval","date":"2023-01-30","arxiv_id":"2301.12700","n_code_links":0,"syntology":null},{"paper":null,"title":"MED-SE: Medical Entity Definition-based Sentence Embedding","date":"2022-12-09","arxiv_id":"2212.04734","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","date":"2022-11-29","arxiv_id":"2211.16285","n_code_links":2,"syntology":null},{"paper":"/paper/english-contrastive-learning-can-learn","title":"English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings","date":"2022-11-11","arxiv_id":"2211.06127","n_code_links":1,"syntology":{"ran":5,"of":10,"unverified":5,"pointer_only":0}}],"papers_shown":30,"tasks":[{"task":"/task/sentence","name":"Sentence","papers":42},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":34},{"task":"/task/sentence-embeddings","name":"Sentence Embeddings","papers":31},{"task":"/task/sts","name":"STS","papers":26},{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":22},{"task":"/task/sentence-embedding","name":"Sentence Embedding","papers":15},{"task":"/task/sentence-embedding-1","name":"Sentence-Embedding","papers":15},{"task":"/task/retrieval","name":"Retrieval","papers":8},{"task":"/task/language-modelling","name":"Language Modelling","papers":7},{"task":"/task/representation-learning","name":"Representation Learning","papers":7},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":5},{"task":"/task/language-modeling","name":"Language Modeling","papers":5},{"task":"/task/information-retrieval","name":"Information Retrieval","papers":4},{"task":"/task/semantic-similarity","name":"Semantic Similarity","papers":4},{"task":"/task/text-similarity","name":"text similarity","papers":4},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":3},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":3},{"task":"/task/word-embeddings","name":"Word Embeddings","papers":3},{"task":"/task/attribute","name":"Attribute","papers":2},{"task":"/task/classification-1","name":"Classification","papers":2}],"tasks_shown":20,"n_tasks":53,"usage_by_year":[{"year":"2021","papers":11},{"year":"2022","papers":14},{"year":"2023","papers":14},{"year":"2024","papers":9},{"year":"2025","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/simcse"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}