{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":15,"n_constructed":2,"n_ran_checked":10,"n_instrument":5,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}},"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":168,"of_with_code":65,"tagged_in_all":168,"counts":{"archive_papers_tagged":168,"with_a_code_link":65,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":168,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"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":15,"n_constructed":2,"n_ran_checked":10,"n_instrument":5,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}},"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/colbert-efficient-and-effective-passage","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colbert-efficient-and-effective-passage#ran","syntology_url":"https://syntology.ai/paper/2004.12832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12832"}},"official":{"repos":["stanford-futuredata/ColBERT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/190407094","slug":"190407094","title":"CEDR: Contextualized Embeddings for Document Ranking","date":"2019-04-15","arxiv_id":"1904.07094","repositories_listed":7,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/190407094#ran","syntology_url":"https://syntology.ai/paper/1904.07094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07094"}},"official":{"repos":["Georgetown-IR-Lab/cedr","Georgetown-IR-Lab/contextualized-reps-for-ranking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-deep-structured-semantic-models-for","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-stage-document-ranking-with-bert#ran","syntology_url":"https://syntology.ai/paper/1910.14424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.14424"}},"official":null}},{"url":"/paper/irgan-a-minimax-game-for-unifying-generative","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/irgan-a-minimax-game-for-unifying-generative#ran","syntology_url":"https://syntology.ai/paper/1705.10513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10513"}},"official":{"repos":["geek-ai/irgan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codec-complex-document-and-entity-collection","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/promptreps-prompting-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2404.18424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18424"}},"official":{"repos":["ielab/promptreps"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rankmamba-benchmarking-mamba-s-document","slug":"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","slug":"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_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/query-augmentation-by-decoding-semantics-from#ran","syntology_url":"https://syntology.ai/paper/2402.15708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15708"}},"official":{"repos":["yeziyi1998/brain-query-augmentation"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/explain-then-rank-scale-calibration-of-neural","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":"/paper/principled-multi-aspect-evaluation-measures","slug":"principled-multi-aspect-evaluation-measures","title":"Principled Multi-Aspect Evaluation Measures of Rankings","date":"2022-12-01","arxiv_id":"2212.00492","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-user-behavior-sequence-modeling-by","slug":"enhancing-user-behavior-sequence-modeling-by","title":"Enhancing User Behavior Sequence Modeling by Generative Tasks for Session Search","date":"2022-08-23","arxiv_id":"2208.10846","repositories_listed":1,"syntology":null},{"url":"/paper/from-easy-to-hard-a-dual-curriculum-learning","slug":"from-easy-to-hard-a-dual-curriculum-learning","title":"From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Ranking","date":"2022-08-22","arxiv_id":"2208.10226","repositories_listed":1,"syntology":null},{"url":"/paper/bert-rankers-are-brittle-a-study-using","slug":"bert-rankers-are-brittle-a-study-using","title":"BERT Rankers are Brittle: a Study using Adversarial Document Perturbations","date":"2022-06-23","arxiv_id":"2206.11724","repositories_listed":1,"syntology":null},{"url":"/paper/long-document-re-ranking-with-modular-re","slug":"long-document-re-ranking-with-modular-re","title":"Long Document Re-ranking with Modular Re-ranker","date":"2022-05-09","arxiv_id":"2205.04275","repositories_listed":1,"syntology":null},{"url":"/paper/socialformer-social-network-inspired-long","slug":"socialformer-social-network-inspired-long","title":"Socialformer: Social Network Inspired Long Document Modeling for Document Ranking","date":"2022-02-22","arxiv_id":"2202.10870","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-approaches-for-building","slug":"transfer-learning-approaches-for-building","title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","date":"2022-01-20","arxiv_id":"2201.08471","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transfer-learning-approaches-for-building#ran","syntology_url":"https://syntology.ai/paper/2201.08471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08471"}},"official":{"repos":["hltcoe/colbert-x"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seed-driven-document-ranking-for-systematic","slug":"seed-driven-document-ranking-for-systematic","title":"Seed-driven Document Ranking for Systematic Reviews: A Reproducibility Study","date":"2021-12-08","arxiv_id":"2112.04090","repositories_listed":1,"syntology":null},{"url":"/paper/siamese-bert-based-model-for-web-search","slug":"siamese-bert-based-model-for-web-search","title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","date":"2021-12-03","arxiv_id":"2112.01810","repositories_listed":1,"syntology":null},{"url":"/paper/fast-forward-indexes-for-efficient-document","slug":"fast-forward-indexes-for-efficient-document","title":"Efficient Neural Ranking using Forward Indexes","date":"2021-10-12","arxiv_id":"2110.06051","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-of-user-behavior","slug":"contrastive-learning-of-user-behavior","title":"Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking","date":"2021-08-24","arxiv_id":"2108.10510","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-facet-selection-by-maximizing-graded","slug":"dynamic-facet-selection-by-maximizing-graded","title":"Dynamic Facet Selection by Maximizing Graded Relevance","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learnt-sparsity-for-effective-and","slug":"learnt-sparsity-for-effective-and","title":"Extractive Explanations for Interpretable Text Ranking","date":"2021-06-23","arxiv_id":"2106.12460","repositories_listed":1,"syntology":null},{"url":"/paper/corpus-level-evaluation-for-event-qa-the","slug":"corpus-level-evaluation-for-event-qa-the","title":"Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence","date":"2021-05-27","arxiv_id":"2105.12936","repositories_listed":1,"syntology":null},{"url":"/paper/intra-document-cascading-learning-to-select","slug":"intra-document-cascading-learning-to-select","title":"Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking","date":"2021-05-20","arxiv_id":"2105.09816","repositories_listed":1,"syntology":null},{"url":"/paper/an-in-depth-analysis-of-passage-level-label","slug":"an-in-depth-analysis-of-passage-level-label","title":"An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking","date":"2021-03-30","arxiv_id":"2103.16669","repositories_listed":1,"syntology":null},{"url":"/paper/improving-bi-encoder-document-ranking-models","slug":"improving-bi-encoder-document-ranking-models","title":"Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation","date":"2021-03-11","arxiv_id":"2103.06523","repositories_listed":1,"syntology":null},{"url":"/paper/openmatch-an-open-source-package-for","slug":"openmatch-an-open-source-package-for","title":"OpenMatch: An Open Source Library for Neu-IR Research","date":"2021-01-30","arxiv_id":"2102.00166","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-calibration-and-uncertainty-of-neural","slug":"on-the-calibration-and-uncertainty-of-neural","title":"On the Calibration and Uncertainty of Neural Learning to Rank Models","date":"2021-01-12","arxiv_id":"2101.04356","repositories_listed":1,"syntology":null},{"url":"/paper/early-exiting-bert-for-efficient-document","slug":"early-exiting-bert-for-efficient-document","title":"Early Exiting BERT for Efficient Document Ranking","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/long-document-ranking-with-query-directed","slug":"long-document-ranking-with-query-directed","title":"Long Document Ranking with Query-Directed Sparse Transformer","date":"2020-10-23","arxiv_id":"2010.12683","repositories_listed":1,"syntology":null},{"url":"/paper/longformer-for-ms-marco-document-re-ranking","slug":"longformer-for-ms-marco-document-re-ranking","title":"Longformer for MS MARCO Document Re-ranking Task","date":"2020-09-20","arxiv_id":"2009.09392","repositories_listed":1,"syntology":null},{"url":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/parade-passage-representation-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2008.09093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09093"}},"official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/fine-grained-relevance-annotations-for-multi","slug":"fine-grained-relevance-annotations-for-multi","title":"Fine-Grained Relevance Annotations for Multi-Task Document Ranking and Question Answering","date":"2020-08-12","arxiv_id":"2008.05363","repositories_listed":1,"syntology":null},{"url":"/paper/bison-bm25-weighted-self-attention-framework","slug":"bison-bm25-weighted-self-attention-framework","title":"GLOW : Global Weighted Self-Attention Network for Web Search","date":"2020-07-10","arxiv_id":"2007.05186","repositories_listed":1,"syntology":null},{"url":"/paper/local-self-attention-over-long-text-for","slug":"local-self-attention-over-long-text-for","title":"Local Self-Attention over Long Text for Efficient Document Retrieval","date":"2020-05-11","arxiv_id":"2005.04908","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/local-self-attention-over-long-text-for#ran","syntology_url":"https://syntology.ai/paper/2005.04908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04908"}},"official":{"repos":["sebastian-hofstaetter/transformer-kernel-ranking"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-document-re-ranking-for","slug":"efficient-document-re-ranking-for","title":"Efficient Document Re-Ranking for Transformers by Precomputing Term Representations","date":"2020-04-29","arxiv_id":"2004.14255","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-information-retrieval-with-bert","slug":"cross-lingual-information-retrieval-with-bert","title":"Cross-lingual Information Retrieval with BERT","date":"2020-04-24","arxiv_id":"2004.13005","repositories_listed":1,"syntology":null},{"url":"/paper/tu-wien-trec-deep-learning-19-simple","slug":"tu-wien-trec-deep-learning-19-simple","title":"TU Wien @ TREC Deep Learning '19 -- Simple Contextualization for Re-ranking","date":"2019-12-03","arxiv_id":"1912.01385","repositories_listed":1,"syntology":null},{"url":"/paper/hare-a-flexible-highlighting-annotator-for","slug":"hare-a-flexible-highlighting-annotator-for","title":"HARE: a Flexible Highlighting Annotator for Ranking and Exploration","date":"2019-08-29","arxiv_id":"1908.11302","repositories_listed":1,"syntology":null},{"url":"/paper/joint-optimization-of-cascade-ranking-models","slug":"joint-optimization-of-cascade-ranking-models","title":"Joint Optimization of Cascade Ranking Models","date":"2019-02-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deeptilebars-visualizing-term-distribution","slug":"deeptilebars-visualizing-term-distribution","title":"DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval","date":"2018-11-01","arxiv_id":"1811.00606","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-for-document-ranking-and","slug":"multi-task-learning-for-document-ranking-and","title":"Multi-Task Learning for Document Ranking and Query Suggestion","date":"2018-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-neural-ad-hoc-ranking-with-kernel","slug":"end-to-end-neural-ad-hoc-ranking-with-kernel","title":"End-to-End Neural Ad-hoc Ranking with Kernel Pooling","date":"2017-06-20","arxiv_id":"1706.06613","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-match-using-local-and-distributed-1","slug":"learning-to-match-using-local-and-distributed-1","title":"Learning to Match Using Local and Distributed Representations of Text for Web Search","date":"2016-10-26","arxiv_id":"1610.08136","repositories_listed":1,"syntology":null},{"url":null,"slug":"bridge-the-gap-between-past-and-future","title":"Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking","date":"2025-05-20","arxiv_id":"2505.14180","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-retrieval-joint-supervision-and","title":"Beyond Retrieval: Joint Supervision and Multimodal Document Ranking for Textbook Question Answering","date":"2025-05-17","arxiv_id":"2505.13520","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-retrieval-framework-with-document","title":"A Unified Retrieval Framework with Document Ranking and EDU Filtering for Multi-document Summarization","date":"2025-04-23","arxiv_id":"2504.16711","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-reproducibility-advancing-zero-shot","title":"Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion","date":"2025-04-09","arxiv_id":"2504.10509","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-re-ranking-emerging-techniques","title":"Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities","date":"2025-03-19","arxiv_id":"2503.14802","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-synthetic-data-strategies-for-domain","title":"On Synthetic Data Strategies for Domain-Specific Generative Retrieval","date":"2025-02-25","arxiv_id":"2502.17957","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-document-modifications-in","title":"White Hat Search Engine Optimization using Large Language Models","date":"2025-02-11","arxiv_id":"2502.07315","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyb2-selecting-key-blocks-is-also-important","title":"KeyB2: Selecting Key Blocks is Also Important for Long Document Ranking with Large Language Models","date":"2024-11-09","arxiv_id":"2411.06254","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-field-adaptive-retrieval","title":"Multi-Field Adaptive Retrieval","date":"2024-10-26","arxiv_id":"2410.20056","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-document-ranking-with-learnable","title":"Efficient Document Ranking with Learnable Late Interactions","date":"2024-06-25","arxiv_id":"2406.17968","repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-kl-divergence-for-document-ranking","title":"Weighted KL-Divergence for Document Ranking Model Refinement","date":"2024-06-10","arxiv_id":"2406.05977","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-evaluation-of-machine-generated","title":"On the Evaluation of Machine-Generated Reports","date":"2024-05-02","arxiv_id":"2405.00982","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-surprising-effectiveness-of-rankers","title":"The Surprising Effectiveness of Rankers Trained on Expanded Queries","date":"2024-04-03","arxiv_id":"2404.02587","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-recall-small-data-the-challenges-of","title":"High Recall, Small Data: The Challenges of Within-System Evaluation in a Live Legal Search System","date":"2024-03-27","arxiv_id":"2403.18962","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-bias-in-a-ranked-list-using-term","title":"Measuring Bias in a Ranked List using Term-based Representations","date":"2024-03-09","arxiv_id":"2403.05975","repositories_listed":0,"syntology":null},{"url":null,"slug":"recency-ranking-by-diversification-of-result","title":"Recency Ranking by Diversification of Result Set","date":"2024-01-26","arxiv_id":"2401.14595","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-sample-efficient-and","title":"Data Augmentation for Sample Efficient and Robust Document Ranking","date":"2023-11-26","arxiv_id":"2311.15426","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-generative-ad-hoc-information","title":"Evaluating Generative Ad Hoc Information Retrieval","date":"2023-11-08","arxiv_id":"2311.04694","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-search-via-neural-contextual","title":"Personalized Search Via Neural Contextual Semantic Relevance Ranking","date":"2023-09-10","arxiv_id":"2309.05113","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-query-rewriting-for-text","title":"Context Aware Query Rewriting for Text Rankers using LLM","date":"2023-08-31","arxiv_id":"2308.16753","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-retrieval-and-multi-stage-text-ranking","title":"Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track","date":"2023-08-23","arxiv_id":"2308.12039","repositories_listed":0,"syntology":null},{"url":null,"slug":"grm-generative-relevance-modeling-using","title":"GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval","date":"2023-06-16","arxiv_id":"2306.09938","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-and-pseudo-relevant-feedback-for","title":"Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval","date":"2023-05-12","arxiv_id":"2305.07477","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-static-pruning-study-on-sparse-neural","title":"A Static Pruning Study on Sparse Neural Retrievers","date":"2023-04-25","arxiv_id":"2304.12702","repositories_listed":0,"syntology":null},{"url":null,"slug":"capot-creating-robust-dense-query-encoders","title":"Noise-Robust Dense Retrieval via Contrastive Alignment Post Training","date":"2023-04-06","arxiv_id":"2304.03401","repositories_listed":0,"syntology":null},{"url":null,"slug":"credence-counterfactual-explanations-for","title":"CREDENCE: Counterfactual Explanations for Document Ranking","date":"2023-02-10","arxiv_id":"2302.04983","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-uniform-architecture","title":"An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking","date":"2023-02-08","arxiv_id":"2302.04112","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-lingual-information-retrieval","title":"Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation","date":"2023-01-29","arxiv_id":"2301.12566","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-rankers-for-effective-screening","title":"Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search","date":"2022-12-18","arxiv_id":"2212.09017","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainability-of-text-processing-and","title":"Explainability of Text Processing and Retrieval Methods: A Critical Survey","date":"2022-12-14","arxiv_id":"2212.07126","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-specific-knowledge-graphs-for-complex","title":"Query-Specific Knowledge Graphs for Complex Finance Topics","date":"2022-11-08","arxiv_id":"2211.04142","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-contrastive-learning-approach-for","title":"Supervised Contrastive Learning Approach for Contextual Ranking","date":"2022-07-07","arxiv_id":"2207.03153","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-value-of-multi-view-learning-1","title":"Exploring the Value of Multi-View Learning for Session-Aware Query Representation","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-query-clarification-and","title":"Interactive Query Clarification and Refinement via User Simulation","date":"2022-05-31","arxiv_id":"2205.15918","repositories_listed":0,"syntology":null},{"url":null,"slug":"prada-practical-black-box-adversarial-attacks","title":"PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models","date":"2022-04-04","arxiv_id":"2204.01321","repositories_listed":0,"syntology":null}],"syntology_records":10,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/task/document-ranking/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/document-ranking/papers/2","json":"/task/document-ranking/papers/2.json","rows":68},{"order":"ran","page":1,"of":1,"url":"/task/document-ranking/papers/ran/1","json":"/task/document-ranking/papers/ran/1.json","rows":9}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"19516db3db005be8a2d5728623c94d08485051c0a1d99c4d224a7535d8b093f9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}