{"url":"/task/semantic-retrieval","name":"Semantic Retrieval","slug":"semantic-retrieval","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":86,"papers_with_code":26,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/semantic-retrieval-on-contract-discovery","slug":"semantic-retrieval-on-contract-discovery","dataset":"Contract Discovery","dataset_url":"/dataset/contract-discovery","rows_in_archive":6,"metrics":["Soft-F1"],"first_row_in_archive_order":{"model":"Human baseline","paper_title":"Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines","paper_url":"/paper/searching-for-legal-clauses-by-analogy-few","paper_date":"2019-11-10","arxiv_id":"1911.03911","code_links":[{"title":"applicaai/contract-discovery","url":"https://github.com/applicaai/contract-discovery"}],"syntology":null}}],"datasets":[{"url":"/dataset/contract-discovery","name":"Contract Discovery","full_name":"","num_papers_in_archive":3},{"url":"/dataset/phrase-in-context","name":"Phrase-in-Context","full_name":"Phrase-in-Context","num_papers_in_archive":1},{"url":"/dataset/speechbrown","name":"Speech Brown","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":26,"of":26,"tagged_in_all":86,"items":[{"url":"/paper/sentence-embedding-models-for-ancient-greek","title":"Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation","date":"2023-08-24","arxiv_id":"2308.13116","repositories_listed":2,"syntology":null},{"url":"/paper/biocpt-contrastive-pre-trained-transformers","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","date":"2023-07-02","arxiv_id":"2307.00589","repositories_listed":2,"syntology":null},{"url":"/paper/revealing-the-importance-of-semantic","title":"Revealing the Importance of Semantic Retrieval for Machine Reading at Scale","date":"2019-09-17","arxiv_id":"1909.08041","repositories_listed":2,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/hdlxgraph-bridging-large-language-models-and","title":"HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases","date":"2025-05-21","arxiv_id":"2505.15701","repositories_listed":1,"syntology":null},{"url":"/paper/andb-breaking-boundaries-with-an-ai-native","title":"AnDB: Breaking Boundaries with an AI-Native Database for Universal Semantic Analysis","date":"2025-02-19","arxiv_id":"2502.13805","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-semantic-retrieval-for-product","title":"Multimodal semantic retrieval for product search","date":"2025-01-13","arxiv_id":"2501.07365","repositories_listed":1,"syntology":null},{"url":"/paper/scbench-a-kv-cache-centric-analysis-of-long","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","date":"2024-12-13","arxiv_id":"2412.10319","repositories_listed":1,"syntology":null},{"url":"/paper/aptness-incorporating-appraisal-theory-and","title":"APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation","date":"2024-07-23","arxiv_id":"2407.21048","repositories_listed":1,"syntology":null},{"url":"/paper/glare-low-light-image-enhancement-via","title":"GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval","date":"2024-07-17","arxiv_id":"2407.12431","repositories_listed":1,"syntology":null},{"url":"/paper/miners-multilingual-language-models-as","title":"MINERS: Multilingual Language Models as Semantic Retrievers","date":"2024-06-11","arxiv_id":"2406.07424","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/llm-based-multi-agent-generation-of-semi","title":"LLM Based Multi-Agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domain","date":"2024-02-21","arxiv_id":"2402.14871","repositories_listed":1,"syntology":null},{"url":"/paper/m4le-a-multi-ability-multi-range-multi-task","title":"M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models","date":"2023-10-30","arxiv_id":"2310.19240","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/if-the-sources-could-talk-evaluating-large","title":"If the Sources Could Talk: Evaluating Large Language Models for Research Assistance in History","date":"2023-10-16","arxiv_id":"2310.10808","repositories_listed":1,"syntology":null},{"url":"/paper/surface-based-retrieval-reduces-perplexity-of","title":"Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models","date":"2023-05-25","arxiv_id":"2305.16243","repositories_listed":1,"syntology":null},{"url":"/paper/intra-class-adaptive-augmentation-with","title":"Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning","date":"2022-11-29","arxiv_id":"2211.16264","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-representation-learning-with","title":"Sentence Representation Learning with Generative Objective rather than Contrastive Objective","date":"2022-10-16","arxiv_id":"2210.08474","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/training-effective-neural-sentence-encoders","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","date":"2022-07-26","arxiv_id":"2207.12759","repositories_listed":1,"syntology":null},{"url":"/paper/pic-a-phrase-in-context-dataset-for-phrase","title":"PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search","date":"2022-07-19","arxiv_id":"2207.09068","repositories_listed":1,"syntology":null},{"url":"/paper/variational-transformer-a-framework-beyond","title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","date":"2022-05-28","arxiv_id":"2205.14458","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-communication-an-information","title":"Semantic Information Recovery in Wireless Networks","date":"2022-04-28","arxiv_id":"2204.13366","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-sentence-representation-for","title":"Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation","date":"2022-03-15","arxiv_id":"2203.07687","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-audio-visual-alignments-in","title":"Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models","date":"2021-07-05","arxiv_id":"2108.02562","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-models-for-the-first-stage-retrieval","title":"Semantic Models for the First-stage Retrieval: A Comprehensive Review","date":"2021-03-08","arxiv_id":"2103.04831","repositories_listed":1,"syntology":null},{"url":"/paper/deep-unsupervised-image-hashing-by-maximizing","title":"Deep Unsupervised Image Hashing by Maximizing Bit Entropy","date":"2020-12-22","arxiv_id":"2012.12334","repositories_listed":1,"syntology":null},{"url":"/paper/searching-for-legal-clauses-by-analogy-few","title":"Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines","date":"2019-11-10","arxiv_id":"1911.03911","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-query-by-example-speech-search-using","title":"Semantic query-by-example speech search using visual grounding","date":"2019-04-15","arxiv_id":"1904.07078","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}],"syntology_records":5,"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"}}