{"url":"/task/sts","name":"STS","slug":"sts","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":334,"papers_with_code":129,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/mteb","name":"MTEB","full_name":"Massive Text Embedding Benchmark","num_papers_in_archive":155},{"url":"/dataset/translated-snli-dataset-in-marathi","name":"Translated SNLI Dataset in Marathi","full_name":"","num_papers_in_archive":1},{"url":"/dataset/assin","name":"ASSIN","full_name":"","num_papers_in_archive":0},{"url":"/dataset/assin2","name":"ASSIN2","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":129,"tagged_in_all":334,"items":[{"url":"/paper/sentence-bert-sentence-embeddings-using","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","date":"2019-08-27","arxiv_id":"1908.10084","repositories_listed":64,"syntology":{"n":58,"n_ran":20,"n_unverified":38,"n_pointer_only":11}},{"url":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","arxiv_id":"2104.08821","repositories_listed":23,"syntology":{"n":30,"n_ran":17,"n_unverified":13,"n_pointer_only":19}},{"url":"/paper/tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","arxiv_id":"2104.06979","repositories_listed":6,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","arxiv_id":"2210.07316","repositories_listed":5,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/medsts-a-resource-for-clinical-semantic","title":"MedSTS: A Resource for Clinical Semantic Textual Similarity","date":"2018-08-28","arxiv_id":"1808.09397","repositories_listed":5,"syntology":null},{"url":"/paper/kornli-and-korsts-new-benchmark-datasets-for","title":"KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding","date":"2020-04-07","arxiv_id":"2004.03289","repositories_listed":3,"syntology":null},{"url":"/paper/semeval-2017-task-1-semantic-textual","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","date":"2017-07-31","arxiv_id":"1708.00055","repositories_listed":3,"syntology":null},{"url":"/paper/pcc-tuning-breaking-the-contrastive-learning","title":"Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity","date":"2024-06-14","arxiv_id":"2406.09790","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-semantic-textual-similarity","title":"Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss","date":"2024-06-08","arxiv_id":"2406.05326","repositories_listed":2,"syntology":null},{"url":"/paper/pixel-sentence-representation-learning","title":"Pixel Sentence Representation Learning","date":"2024-02-13","arxiv_id":"2402.08183","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/deelm-dependency-enhanced-large-language","title":"BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings","date":"2023-11-09","arxiv_id":"2311.05296","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","arxiv_id":"2309.12871","repositories_listed":2,"syntology":null},{"url":"/paper/infocse-information-aggregated-contrastive","title":"InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings","date":"2022-10-08","arxiv_id":"2210.06432","repositories_listed":2,"syntology":null},{"url":"/paper/esimcse-enhanced-sample-building-method-for","title":"ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding","date":"2021-09-09","arxiv_id":"2109.04380","repositories_listed":2,"syntology":null},{"url":"/paper/smoothed-contrastive-learning-for","title":"Smoothed Contrastive Learning for Unsupervised Sentence Embedding","date":"2021-09-09","arxiv_id":"2109.04321","repositories_listed":2,"syntology":null},{"url":"/paper/sentence-t5-scalable-sentence-encoders-from","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","date":"2021-08-19","arxiv_id":"2108.08877","repositories_listed":2,"syntology":null},{"url":"/paper/hybrid-model-for-patent-classification-using","title":"PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERT","date":"2021-03-22","arxiv_id":"2103.11933","repositories_listed":2,"syntology":null},{"url":"/paper/ffci-a-framework-for-interpretable-automatic","title":"FFCI: A Framework for Interpretable Automatic Evaluation of Summarization","date":"2020-11-27","arxiv_id":"2011.13662","repositories_listed":2,"syntology":null},{"url":"/paper/dont-settle-for-average-go-for-the-max-fuzzy-1","title":"Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors","date":"2019-04-30","arxiv_id":"1904.13264","repositories_listed":2,"syntology":null},{"url":"/paper/contrastive-prompting-enhances-sentence","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","date":"2025-05-19","arxiv_id":"2505.12831","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transformer-embeddings","title":"Parameter-Efficient Transformer Embeddings","date":"2025-05-04","arxiv_id":"2505.02266","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-for-japanese-sentence","title":"Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation","date":"2025-03-12","arxiv_id":"2503.09094","repositories_listed":1,"syntology":null},{"url":"/paper/textinplace-indoor-visual-place-recognition","title":"TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification","date":"2025-03-09","arxiv_id":"2503.06501","repositories_listed":1,"syntology":null},{"url":"/paper/finmteb-finance-massive-text-embedding","title":"FinMTEB: Finance Massive Text Embedding Benchmark","date":"2025-02-16","arxiv_id":"2502.10990","repositories_listed":1,"syntology":null},{"url":"/paper/fast-precise-thompson-sampling-for-bayesian","title":"Fast, Precise Thompson Sampling for Bayesian Optimization","date":"2024-11-26","arxiv_id":"2411.17071","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/2d-matryoshka-training-for-information","title":"2D Matryoshka Training for Information Retrieval","date":"2024-11-26","arxiv_id":"2411.17299","repositories_listed":1,"syntology":null},{"url":"/paper/geneol-harnessing-the-generative-power-of","title":"GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings","date":"2024-10-18","arxiv_id":"2410.14635","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/distilling-monolingual-and-crosslingual-word","title":"Distilling Monolingual and Crosslingual Word-in-Context Representations","date":"2024-09-13","arxiv_id":"2409.08719","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00690","title":"Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning","date":"2024-08-01","arxiv_id":"2408.00690","repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}