{"url":"/task/sts-benchmark","name":"STS Benchmark","slug":"sts-benchmark","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":16,"papers_with_code":7,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/humaneval","name":"HumanEval","full_name":"","num_papers_in_archive":1201},{"url":"/dataset/sts-benchmark","name":"STS Benchmark","full_name":"Semantic Textual Similarity","num_papers_in_archive":45}],"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":7,"of":7,"tagged_in_all":16,"items":[{"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/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/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/are-electra-s-sentence-embeddings-beyond","title":"Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity","date":"2024-02-20","arxiv_id":"2402.13130","repositories_listed":1,"syntology":null},{"url":"/paper/jcse-contrastive-learning-of-japanese","title":"JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications","date":"2023-01-19","arxiv_id":"2301.08193","repositories_listed":1,"syntology":null},{"url":"/paper/paraphrase-thought-sentence-embedding-module","title":"Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition","date":"2018-08-16","arxiv_id":"1808.05505","repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantic-textual-similarity-from","title":"Learning Semantic Textual Similarity from Conversations","date":"2018-04-20","arxiv_id":"1804.07754","repositories_listed":1,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}}],"syntology_records":2,"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"}}