{"url":"/task/document-ranking","name":"Document Ranking","slug":"document-ranking","description_markdown":"Sort documents according to some criterion so that the \"best\" results appear early in the result list displayed to the user (Source: Wikipedia).","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":168,"papers_with_code":65,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":7,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/document-ranking-on-dareczech","slug":"document-ranking-on-dareczech","dataset":"DaReCzech","dataset_url":"/dataset/dareczech","rows_in_archive":3,"metrics":["P@10"],"first_row_in_archive_order":{"model":"Query-doc RobeCzech (Roberta-base)","paper_title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","paper_url":"/paper/siamese-bert-based-model-for-web-search","paper_date":"2021-12-03","arxiv_id":"2112.01810","code_links":[{"title":"seznam/dareczech","url":"https://github.com/seznam/dareczech"}],"syntology":null}},{"leaderboard":"/sota/document-ranking-on-clueweb09-b","slug":"document-ranking-on-clueweb09-b","dataset":"ClueWeb09-B","dataset_url":"/dataset/clue","rows_in_archive":1,"metrics":["ERR@20","nDCG@20"],"first_row_in_archive_order":{"model":"XLNet","paper_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","paper_url":"/paper/xlnet-generalized-autoregressive-pretraining","paper_date":"2019-06-19","arxiv_id":"1906.08237","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}],"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":3}}}],"datasets":[{"url":"/dataset/clue","name":"CLUE","full_name":"Chinese Language Understanding Evaluation Benchmark","num_papers_in_archive":99},{"url":"/dataset/mq2008","name":"MQ2008","full_name":"","num_papers_in_archive":31},{"url":"/dataset/qulac","name":"Qulac","full_name":null,"num_papers_in_archive":19},{"url":"/dataset/mslr-web30k","name":"MSLR WEB30K","full_name":"Microsoft Learning to Rank Datasets-30k","num_papers_in_archive":9},{"url":"/dataset/dareczech","name":"DaReCzech","full_name":"Dataset for text relevance ranking in Czech","num_papers_in_archive":4},{"url":"/dataset/basir","name":"BASIR","full_name":"BASIR_Budget_Assisted_Sectoral_Impact_Ranking","num_papers_in_archive":1},{"url":"/dataset/istella-letor","name":"Istella LETOR","full_name":"Istella Learning to Rank","num_papers_in_archive":1}],"subtasks":[{"url":"/task/session-search","name":"Session Search"}],"parent_tasks":[{"url":"/task/ad-hoc-information-retrieval","name":"Ad-Hoc Information Retrieval"}],"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":65,"tagged_in_all":168,"items":[{"url":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","repositories_listed":27,"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":3}},{"url":"/paper/colbert-efficient-and-effective-passage","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","date":"2020-04-27","arxiv_id":"2004.12832","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/190407094","title":"CEDR: Contextualized Embeddings for Document Ranking","date":"2019-04-15","arxiv_id":"1904.07094","repositories_listed":7,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/learning-deep-structured-semantic-models-for","title":"Learning deep structured semantic models for web search using clickthrough data","date":"2013-10-27","arxiv_id":null,"repositories_listed":6,"syntology":null},{"url":"/paper/context-attentive-document-ranking-and-query","title":"Context Attentive Document Ranking and Query Suggestion","date":"2019-06-05","arxiv_id":"1906.02329","repositories_listed":5,"syntology":null},{"url":"/paper/the-expando-mono-duo-design-pattern-for-text","title":"The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models","date":"2021-01-14","arxiv_id":"2101.05667","repositories_listed":4,"syntology":null},{"url":"/paper/simplified-tinybert-knowledge-distillation","title":"Simplified TinyBERT: Knowledge Distillation for Document Retrieval","date":"2020-09-16","arxiv_id":"2009.07531","repositories_listed":4,"syntology":null},{"url":"/paper/neural-vector-spaces-for-unsupervised","title":"Neural Vector Spaces for Unsupervised Information Retrieval","date":"2017-08-09","arxiv_id":"1708.02702","repositories_listed":4,"syntology":null},{"url":"/paper/understanding-performance-of-long-document","title":"Understanding Performance of Long-Document Ranking Models through Comprehensive Evaluation and Leaderboarding","date":"2022-07-04","arxiv_id":"2207.01262","repositories_listed":3,"syntology":null},{"url":"/paper/multi-stage-document-ranking-with-bert","title":"Multi-Stage Document Ranking with BERT","date":"2019-10-31","arxiv_id":"1910.14424","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/irgan-a-minimax-game-for-unifying-generative","title":"IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models","date":"2017-05-30","arxiv_id":"1705.10513","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/codec-complex-document-and-entity-collection","title":"CODEC: Complex Document and Entity Collection","date":"2022-05-09","arxiv_id":"2205.04546","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-classic-and-neural-lexical","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","date":"2021-02-12","arxiv_id":"2102.06815","repositories_listed":2,"syntology":null},{"url":"/paper/traditional-ir-rivals-neural-models-on-the-ms","title":"Traditional IR rivals neural models on the MS MARCO Document Ranking Leaderboard","date":"2020-12-15","arxiv_id":"2012.08020","repositories_listed":2,"syntology":null},{"url":"/paper/document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","arxiv_id":"2003.06713","repositories_listed":2,"syntology":null},{"url":"/paper/precise-zero-shot-pointwise-ranking-with-llms","title":"Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information","date":"2025-06-12","arxiv_id":"2506.10859","repositories_listed":1,"syntology":null},{"url":"/paper/how-do-large-language-models-understand","title":"How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective","date":"2025-04-10","arxiv_id":"2504.07898","repositories_listed":1,"syntology":null},{"url":"/paper/distillation-and-refinement-of-reasoning-in","title":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","date":"2025-04-04","arxiv_id":"2504.03947","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-questions-leveraging-colbert-for","title":"Beyond Questions: Leveraging ColBERT for Keyphrase Search","date":"2024-12-04","arxiv_id":"2412.03193","repositories_listed":1,"syntology":null},{"url":"/paper/dyvo-dynamic-vocabularies-for-learned-sparse","title":"DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities","date":"2024-10-10","arxiv_id":"2410.07722","repositories_listed":1,"syntology":null},{"url":"/paper/re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","repositories_listed":1,"syntology":null},{"url":"/paper/promptreps-prompting-large-language-models-to","title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","date":"2024-04-29","arxiv_id":"2404.18424","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/rankmamba-benchmarking-mamba-s-document","title":"RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers","date":"2024-03-27","arxiv_id":"2403.18276","repositories_listed":1,"syntology":null},{"url":"/paper/query-augmentation-by-decoding-semantics-from","title":"Query Augmentation by Decoding Semantics from Brain Signals","date":"2024-02-24","arxiv_id":"2402.15708","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/explain-then-rank-scale-calibration-of-neural","title":"Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMs","date":"2024-02-19","arxiv_id":"2402.12276","repositories_listed":1,"syntology":null},{"url":"/paper/open-source-large-language-models-are-strong","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","date":"2023-10-20","arxiv_id":"2310.13243","repositories_listed":1,"syntology":null},{"url":"/paper/a-setwise-approach-for-effective-and-highly","title":"A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models","date":"2023-10-14","arxiv_id":"2310.09497","repositories_listed":1,"syntology":null},{"url":"/paper/fusion-in-t5-unifying-document-ranking","title":"Fusion-in-T5: Unifying Document Ranking Signals for Improved Information Retrieval","date":"2023-05-24","arxiv_id":"2305.14685","repositories_listed":1,"syntology":null},{"url":"/paper/pretraining-de-biased-language-model-with","title":"Pretraining De-Biased Language Model with Large-scale Click Logs for Document Ranking","date":"2023-02-27","arxiv_id":"2302.13498","repositories_listed":1,"syntology":null},{"url":"/paper/lead-liberal-feature-based-distillation-for","title":"LEAD: Liberal Feature-based Distillation for Dense Retrieval","date":"2022-12-10","arxiv_id":"2212.05225","repositories_listed":1,"syntology":null}],"syntology_records":7,"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"}}