{"url":"/task/zero-shot-text-search","name":"Zero-shot Text Search","slug":"zero-shot-text-search","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":14,"papers_with_code":14,"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":16,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/natural-questions","name":"Natural Questions","full_name":"","num_papers_in_archive":1404},{"url":"/dataset/dbpedia","name":"DBpedia","full_name":"DBpedia","num_papers_in_archive":597},{"url":"/dataset/fever","name":"FEVER","full_name":"Fact Extraction and VERification","num_papers_in_archive":498},{"url":"/dataset/beir","name":"BEIR","full_name":"Benchmarking IR","num_papers_in_archive":311},{"url":"/dataset/bioasq","name":"BioASQ","full_name":"Biomedical Semantic Indexing and Question Answering","num_papers_in_archive":192},{"url":"/dataset/scifact","name":"SciFact","full_name":"","num_papers_in_archive":116},{"url":"/dataset/trec-covid","name":"TREC-COVID","full_name":"","num_papers_in_archive":73},{"url":"/dataset/scidocs","name":"SciDocs","full_name":"SciDocs","num_papers_in_archive":57},{"url":"/dataset/climate-fever","name":"CLIMATE-FEVER","full_name":"","num_papers_in_archive":38},{"url":"/dataset/robust04","name":"Robust04","full_name":"","num_papers_in_archive":13},{"url":"/dataset/cqadupstack","name":"CQADupStack","full_name":"","num_papers_in_archive":5},{"url":"/dataset/nfcorpus","name":"NFCorpus","full_name":"","num_papers_in_archive":5},{"url":"/dataset/trec-news-1","name":"TREC-News","full_name":"","num_papers_in_archive":3},{"url":"/dataset/signal-1m-related-tweets","name":"Signal-1M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/webis-touche-2020","name":"Webis-Touché-2020","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cfever","name":"CFEVER","full_name":"","num_papers_in_archive":1}],"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":14,"of":14,"tagged_in_all":14,"items":[{"url":"/paper/gpl-generative-pseudo-labeling-for","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","date":"2021-12-14","arxiv_id":"2112.07577","repositories_listed":5,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/approximate-nearest-neighbor-negative","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","date":"2020-07-01","arxiv_id":"2007.00808","repositories_listed":5,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/efficiently-teaching-an-effective-dense","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","date":"2021-04-14","arxiv_id":"2104.06967","repositories_listed":4,"syntology":null},{"url":"/paper/bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","repositories_listed":3,"syntology":{"n":22,"n_ran":10,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/colbertv2-effective-and-efficient-retrieval","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","date":"2021-12-02","arxiv_id":"2112.01488","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/large-dual-encoders-are-generalizable","title":"Large Dual Encoders Are Generalizable Retrievers","date":"2021-12-15","arxiv_id":"2112.07899","repositories_listed":2,"syntology":null},{"url":"/paper/splade-v2-sparse-lexical-and-expansion-model","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","date":"2021-09-21","arxiv_id":"2109.10086","repositories_listed":2,"syntology":null},{"url":"/paper/blended-rag-improving-rag-retriever-augmented","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","date":"2024-03-22","arxiv_id":"2404.07220","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/retromae-v2-duplex-masked-auto-encoder-for","title":"RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","date":"2022-11-16","arxiv_id":"2211.08769","repositories_listed":1,"syntology":null},{"url":"/paper/coco-dr-combating-distribution-shifts-in-zero","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","date":"2022-10-27","arxiv_id":"2210.15212","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/text-and-code-embeddings-by-contrastive-pre","title":"Text and Code Embeddings by Contrastive Pre-Training","date":"2022-01-24","arxiv_id":"2201.10005","repositories_listed":1,"syntology":null},{"url":"/paper/200210957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","date":"2020-02-25","arxiv_id":"2002.10957","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-question-generation-from-knowledge","title":"Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types","date":"2018-02-19","arxiv_id":"1802.06842","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}}],"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"}}