{"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/text-to-sql","name":"Text-To-SQL","slug":"text-to-sql","description_markdown":"**Text-to-SQL** is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [SyntaxSQLNet](https://arxiv.org/pdf/1810.05237v2.pdf) )</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"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":424,"papers_with_code":209,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"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":21,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/text-to-sql-on-bird-big-bench-for-large-scale","slug":"text-to-sql-on-bird-big-bench-for-large-scale","dataset":"BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)","dataset_url":"/dataset/bird-sql","rows_in_archive":41,"metrics":["Execution Accuracy % (Test)","Execution Accuracy % (Dev)","Execution Accurarcy (Human)"],"first_row_in_archive_order":{"model":"XiYan-SQL","paper_title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","paper_url":"/paper/xiyan-sql-a-multi-generator-ensemble","paper_date":"2024-11-13","arxiv_id":"2411.08599","code_links":[{"title":"XGenerationLab/XiYan-SQL","url":"https://github.com/XGenerationLab/XiYan-SQL"},{"title":"xgenerationlab/xiyan_mcp_server","url":"https://github.com/xgenerationlab/xiyan_mcp_server"},{"title":"XGenerationLab/M-Schema","url":"https://github.com/XGenerationLab/M-Schema"},{"title":"xgenerationlab/xiyan-dbdescgen","url":"https://github.com/xgenerationlab/xiyan-dbdescgen"},{"title":"XGenerationLab/XiYan-DateResolver","url":"https://github.com/XGenerationLab/XiYan-DateResolver"}],"syntology":null}},{"leaderboard":"/sota/text-to-sql-on-spider","slug":"text-to-sql-on-spider","dataset":"spider","dataset_url":"/dataset/spider-realistic","rows_in_archive":20,"metrics":["Execution Accuracy (Test)","Exact Match Accuracy (Test)","Execution Accuracy (Dev)","Exact Match Accuracy (Dev)"],"first_row_in_archive_order":{"model":"XiYan-SQL","paper_title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","paper_url":"/paper/xiyan-sql-a-multi-generator-ensemble","paper_date":"2024-11-13","arxiv_id":"2411.08599","code_links":[{"title":"XGenerationLab/XiYan-SQL","url":"https://github.com/XGenerationLab/XiYan-SQL"},{"title":"xgenerationlab/xiyan_mcp_server","url":"https://github.com/xgenerationlab/xiyan_mcp_server"},{"title":"XGenerationLab/M-Schema","url":"https://github.com/XGenerationLab/M-Schema"},{"title":"xgenerationlab/xiyan-dbdescgen","url":"https://github.com/xgenerationlab/xiyan-dbdescgen"},{"title":"XGenerationLab/XiYan-DateResolver","url":"https://github.com/XGenerationLab/XiYan-DateResolver"}],"syntology":null}},{"leaderboard":"/sota/text-to-sql-on-spider-2-0","slug":"text-to-sql-on-spider-2-0","dataset":"Spider 2.0","dataset_url":"/dataset/spider-2-0","rows_in_archive":8,"metrics":["Success Rate"],"first_row_in_archive_order":{"model":"Spider-Agent + o1-preview","paper_title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","paper_url":"/paper/spider-2-0-evaluating-language-models-on-real","paper_date":"2024-11-12","arxiv_id":"2411.07763","code_links":[],"syntology":null}},{"leaderboard":"/sota/text-to-sql-on-sparc","slug":"text-to-sql-on-sparc","dataset":"SParC","dataset_url":"/dataset/sparc","rows_in_archive":7,"metrics":["interaction match accuracy","question match accuracy"],"first_row_in_archive_order":{"model":"RASAT+PICARD","paper_title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","paper_url":"/paper/rasat-integrating-relational-structures-into","paper_date":"2022-05-14","arxiv_id":"2205.06983","code_links":[{"title":"lumia-group/rasat","url":"https://github.com/lumia-group/rasat"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rasat-integrating-relational-structures-into#ran","syntology_url":"https://syntology.ai/paper/2205.06983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06983"}},"official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/text-to-sql-on-spider-1","slug":"text-to-sql-on-spider-1","dataset":"SPIDER","dataset_url":"/dataset/spider-realistic","rows_in_archive":4,"metrics":["Exact Match Accuracy (in Dev)","Execution Accuracy (in Dev)"],"first_row_in_archive_order":{"model":"T5-3B+PICARD","paper_title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","paper_url":"/paper/picard-parsing-incrementally-for-constrained","paper_date":"2021-09-10","arxiv_id":"2109.05093","code_links":[{"title":"servicenow/picard","url":"https://github.com/servicenow/picard"},{"title":"ElementAI/picard","url":"https://github.com/ElementAI/picard"},{"title":"yangyucheng000/Paper-3","url":"https://github.com/yangyucheng000/Paper-3/tree/main/acm-mm-2023-picr-master"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/picard-parsing-incrementally-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2109.05093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05093"}},"official":{"repos":["ElementAI/picard"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/text-to-sql-on-kaggledbqa","slug":"text-to-sql-on-kaggledbqa","dataset":"KaggleDBQA","dataset_url":"/dataset/kaggledbqa","rows_in_archive":2,"metrics":["Exact Match (EM)"],"first_row_in_archive_order":{"model":"RAT-SQL","paper_title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","paper_url":"/paper/kaggledbqa-realistic-evaluation-of-text-to","paper_date":"2021-06-22","arxiv_id":"2106.11455","code_links":[{"title":"saparina/text2sql-nlvariation","url":"https://github.com/saparina/text2sql-nlvariation"},{"title":"chiahsuan156/KaggleDBQA","url":"https://github.com/chiahsuan156/KaggleDBQA"}],"syntology":null}},{"leaderboard":"/sota/text-to-sql-on-2d-kitti-cars-easy","slug":"text-to-sql-on-2d-kitti-cars-easy","dataset":"2D KITTI Cars Easy","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["0..5sec"],"first_row_in_archive_order":{"model":"sdfa","paper_title":"Non-local Neural Networks","paper_url":"/paper/non-local-neural-networks","paper_date":"2017-11-21","arxiv_id":"1711.07971","code_links":[{"title":"facebookresearch/detectron","url":"https://github.com/facebookresearch/detectron"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"MIT-HAN-LAB/temporal-shift-module","url":"https://github.com/MIT-HAN-LAB/temporal-shift-module"},{"title":"facebookresearch/video-nonlocal-net","url":"https://github.com/facebookresearch/video-nonlocal-net"},{"title":"cmsflash/efficient-attention","url":"https://github.com/cmsflash/efficient-attention"},{"title":"tea1528/Non-Local-NN-Pytorch","url":"https://github.com/tea1528/Non-Local-NN-Pytorch"},{"title":"vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks","url":"https://github.com/vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks"},{"title":"franknb/Self-attention-DCGAN","url":"https://github.com/franknb/Self-attention-DCGAN"},{"title":"mirthai/csa-net","url":"https://github.com/mirthai/csa-net"},{"title":"tinymilky/RSANet","url":"https://github.com/tinymilky/RSANet"},{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"},{"title":"seominseok0429/inception-I3D-NON-LOCAL","url":"https://github.com/seominseok0429/inception-I3D-NON-LOCAL"},{"title":"jpviguerasguillen/feedback-non-local-attention-fnla","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention-fnla"},{"title":"JiaPeng1234/MRI-Segmentation-Transformer","url":"https://github.com/JiaPeng1234/MRI-Segmentation-Transformer"},{"title":"jpviguerasguillen/feedback-non-local-attention_fNLA","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention_fNLA"},{"title":"huyz1117/Non_Local_Net_TensorFlow","url":"https://github.com/huyz1117/Non_Local_Net_TensorFlow"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/Non_local"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/Non_local"},{"title":"WavesUR/embedded_TSM","url":"https://github.com/WavesUR/embedded_TSM"},{"title":"sunutf/TSM","url":"https://github.com/sunutf/TSM"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/I3D"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/Non_local"},{"title":"changliu816/CV-paper-review","url":"https://github.com/changliu816/CV-paper-review"},{"title":"jiajunhua/facebookresearch-Detectron","url":"https://github.com/jiajunhua/facebookresearch-Detectron"},{"title":"owena11/papers","url":"https://github.com/owena11/papers"},{"title":"LRacoci/permutation-graphml","url":"https://github.com/LRacoci/permutation-graphml"},{"title":"jordiae/DeepLearning-MAI","url":"https://github.com/jordiae/DeepLearning-MAI"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/Non_local"},{"title":"Aprilkaka/nonlocal_mindspore","url":"https://github.com/Aprilkaka/nonlocal_mindspore"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/Non_local"},{"title":"rijuldhir/TSM","url":"https://github.com/rijuldhir/TSM"}],"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}},"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-to-sql-on-sede","slug":"text-to-sql-on-sede","dataset":"SEDE","dataset_url":"/dataset/sede","rows_in_archive":1,"metrics":["PCM-F1 (dev)","PCM-F1 (test)"],"first_row_in_archive_order":{"model":"T5-Large","paper_title":"Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data","paper_url":"/paper/text-to-sql-in-the-wild-a-naturally-occurring","paper_date":"2021-06-09","arxiv_id":"2106.05006","code_links":[{"title":"hirupert/sede","url":"https://github.com/hirupert/sede"}],"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/text-to-sql-in-the-wild-a-naturally-occurring#ran","syntology_url":"https://syntology.ai/paper/2106.05006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05006"}},"official":{"repos":["hirupert/sede"],"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"]}}}},{"leaderboard":"/sota/text-to-sql-on-sql-eval-1","slug":"text-to-sql-on-sql-eval-1","dataset":"SQL-Eval","dataset_url":"/dataset/sql-eval-1","rows_in_archive":1,"metrics":["Execution Accuracy"],"first_row_in_archive_order":{"model":"XiYan-SQL","paper_title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","paper_url":"/paper/xiyan-sql-a-multi-generator-ensemble","paper_date":"2024-11-13","arxiv_id":"2411.08599","code_links":[{"title":"XGenerationLab/XiYan-SQL","url":"https://github.com/XGenerationLab/XiYan-SQL"},{"title":"xgenerationlab/xiyan_mcp_server","url":"https://github.com/xgenerationlab/xiyan_mcp_server"},{"title":"XGenerationLab/M-Schema","url":"https://github.com/XGenerationLab/M-Schema"},{"title":"xgenerationlab/xiyan-dbdescgen","url":"https://github.com/xgenerationlab/xiyan-dbdescgen"},{"title":"XGenerationLab/XiYan-DateResolver","url":"https://github.com/XGenerationLab/XiYan-DateResolver"}],"syntology":null}},{"leaderboard":"/sota/text-to-sql-on-text-to-sql","slug":"text-to-sql-on-text-to-sql","dataset":"Text-To-SQL","dataset_url":null,"rows_in_archive":1,"metrics":["0-shot MRR"],"first_row_in_archive_order":{"model":"Orange-mini","paper_title":"OpenGrok: Enhancing SNS Data Processing with Distilled Knowledge and Mask-like Mechanisms","paper_url":"/paper/opengrok-enhancing-sns-data-processing-with","paper_date":"2025-02-11","arxiv_id":"2502.07312","code_links":[{"title":"Lumen-Laboratory/OpenGrok","url":"https://github.com/Lumen-Laboratory/OpenGrok"}],"syntology":null}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/spider-realistic","name":"Spider-Realistic","full_name":"","num_papers_in_archive":91},{"url":"/dataset/hybridqa","name":"HybridQA","full_name":"","num_papers_in_archive":70},{"url":"/dataset/sparc","name":"SParC","full_name":"Semantic Parsing in Context","num_papers_in_archive":59},{"url":"/dataset/cosql","name":"CoSQL","full_name":"Conversational Text-to-SQL Challenge","num_papers_in_archive":45},{"url":"/dataset/kaggledbqa","name":"KaggleDBQA","full_name":"KaggleDBQA: Realistic Text-to-SQL dataset","num_papers_in_archive":28},{"url":"/dataset/bird-sql","name":"BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)","full_name":"","num_papers_in_archive":15},{"url":"/dataset/sede","name":"SEDE","full_name":"Stack Exchange Data Explorer","num_papers_in_archive":11},{"url":"/dataset/spider-2-0","name":"Spider 2.0","full_name":"Spider 2.0","num_papers_in_archive":8},{"url":"/dataset/splash","name":"SPLASH","full_name":"","num_papers_in_archive":6},{"url":"/dataset/adveta","name":"ADVETA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/multispider","name":"MultiSpider","full_name":"","num_papers_in_archive":4},{"url":"/dataset/triagesql","name":"TriageSQL","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/sql-eval-1","name":"SQL-Eval","full_name":"","num_papers_in_archive":2},{"url":"/dataset/vitext2sql","name":"ViText2SQL","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/car-bi","name":"Car_bi","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mmsql","name":"MMSQL","full_name":"Multi-Turn Multi-Type Text-to-SQL test suit","num_papers_in_archive":1},{"url":"/dataset/tur2sql","name":"TUR2SQL","full_name":"TUR2SQL","num_papers_in_archive":1},{"url":"/dataset/nstext2sql-an-open-source-text-to-sql-dataset","name":"NSText2SQL: An Open Source Text-to-SQL Dataset for Foundation Model Training","full_name":"","num_papers_in_archive":0},{"url":"/dataset/turspider-1","name":"TURSpider","full_name":"TURSpider: A Turkish Text-to-SQL Dataset","num_papers_in_archive":0},{"url":"/dataset/turspider","name":"TURSpider: A Turkish Text-to-SQL Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/mmsql-performance","name":"MMSQL performance"}],"parent_tasks":[{"url":"/task/semantic-parsing","name":"Semantic Parsing"}],"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":5,"rows_per_page":100,"shown":100,"of":424,"of_with_code":209,"tagged_in_all":424,"counts":{"archive_papers_tagged":424,"with_a_code_link":209,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":424,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":14,"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/non-local-neural-networks","slug":"non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","repositories_listed":32,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}},"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/seq2sql-generating-structured-queries-from","slug":"seq2sql-generating-structured-queries-from","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","date":"2017-08-31","arxiv_id":"1709.00103","repositories_listed":15,"syntology":null},{"url":"/paper/sqlnet-generating-structured-queries-from","slug":"sqlnet-generating-structured-queries-from","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","date":"2017-11-13","arxiv_id":"1711.04436","repositories_listed":13,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/sqlnet-generating-structured-queries-from#ran","syntology_url":"https://syntology.ai/paper/1711.04436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.04436"}},"official":null}},{"url":"/paper/spider-a-large-scale-human-labeled-dataset","slug":"spider-a-large-scale-human-labeled-dataset","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","date":"2018-09-24","arxiv_id":"1809.08887","repositories_listed":6,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 3 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spider-a-large-scale-human-labeled-dataset#ran","syntology_url":"https://syntology.ai/paper/1809.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.08887"}},"official":{"repos":["taoyds/spider"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/xiyan-sql-a-multi-generator-ensemble","slug":"xiyan-sql-a-multi-generator-ensemble","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","date":"2024-11-13","arxiv_id":"2411.08599","repositories_listed":5,"syntology":null},{"url":"/paper/content-enhanced-bert-based-text-to-sql","slug":"content-enhanced-bert-based-text-to-sql","title":"Content Enhanced BERT-based Text-to-SQL Generation","date":"2019-10-16","arxiv_id":"1910.07179","repositories_listed":5,"syntology":null},{"url":"/paper/towards-complex-text-to-sql-in-cross-domain","slug":"towards-complex-text-to-sql-in-cross-domain","title":"Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation","date":"2019-05-20","arxiv_id":"1905.08205","repositories_listed":5,"syntology":{"n":20,"n_ran":20,"n_constructed":0,"n_ran_checked":20,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":12,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-complex-text-to-sql-in-cross-domain#ran","syntology_url":"https://syntology.ai/paper/1905.08205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08205"}},"official":{"repos":["zhanzecheng/IRNet","zhanzecheng/IRNet-1"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/xiyan-sql-a-novel-multi-generator-framework","slug":"xiyan-sql-a-novel-multi-generator-framework","title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","date":"2025-07-07","arxiv_id":"2507.04701","repositories_listed":4,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xiyan-sql-a-novel-multi-generator-framework#ran","syntology_url":"https://syntology.ai/paper/2507.04701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04701"}},"official":{"repos":["XGenerationLab/XiYan-SQL"],"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/rat-sql-relation-aware-schema-encoding-and-1","slug":"rat-sql-relation-aware-schema-encoding-and-1","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","date":"2019-11-10","arxiv_id":"1911.04942","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rat-sql-relation-aware-schema-encoding-and-1#ran","syntology_url":"https://syntology.ai/paper/1911.04942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04942"}},"official":{"repos":["Microsoft/rat-sql"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sparc-cross-domain-semantic-parsing-in","slug":"sparc-cross-domain-semantic-parsing-in","title":"SParC: Cross-Domain Semantic Parsing in Context","date":"2019-06-05","arxiv_id":"1906.02285","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sparc-cross-domain-semantic-parsing-in#ran","syntology_url":"https://syntology.ai/paper/1906.02285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02285"}},"official":{"repos":["ryanzhumich/editsql"],"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","unlocated"]}}},{"url":"/paper/natural-sql-making-sql-easier-to-infer-from","slug":"natural-sql-making-sql-easier-to-infer-from","title":"Natural SQL: Making SQL Easier to Infer from Natural Language Specifications","date":"2021-09-11","arxiv_id":"2109.05153","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/natural-sql-making-sql-easier-to-infer-from#ran","syntology_url":"https://syntology.ai/paper/2109.05153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05153"}},"official":{"repos":["ygan/natsql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/picard-parsing-incrementally-for-constrained","slug":"picard-parsing-incrementally-for-constrained","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","date":"2021-09-10","arxiv_id":"2109.05093","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/picard-parsing-incrementally-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2109.05093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05093"}},"official":{"repos":["ElementAI/picard"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-contextual-representations-for","slug":"learning-contextual-representations-for","title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","date":"2020-12-18","arxiv_id":"2012.10309","repositories_listed":3,"syntology":null},{"url":"/paper/semantic-evaluation-for-text-to-sql-with","slug":"semantic-evaluation-for-text-to-sql-with","title":"Semantic Evaluation for Text-to-SQL with Distilled Test Suites","date":"2020-10-06","arxiv_id":"2010.02840","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantic-evaluation-for-text-to-sql-with#ran","syntology_url":"https://syntology.ai/paper/2010.02840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02840"}},"official":{"repos":["ruiqi-zhong/TestSuiteEval"],"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/cosql-a-conversational-text-to-sql-challenge","slug":"cosql-a-conversational-text-to-sql-challenge","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","date":"2019-09-11","arxiv_id":"1909.05378","repositories_listed":3,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cosql-a-conversational-text-to-sql-challenge#ran","syntology_url":"https://syntology.ai/paper/1909.05378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05378"}},"official":{"repos":["ryanzhumich/editsql"],"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/editing-based-sql-query-generation-for-cross","slug":"editing-based-sql-query-generation-for-cross","title":"Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions","date":"2019-09-02","arxiv_id":"1909.00786","repositories_listed":3,"syntology":null},{"url":"/paper/towards-automated-cross-domain-exploratory","slug":"towards-automated-cross-domain-exploratory","title":"Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models","date":"2024-12-10","arxiv_id":"2412.07214","repositories_listed":2,"syntology":null},{"url":"/paper/esm-modern-insights-into-perspective-on-text","slug":"esm-modern-insights-into-perspective-on-text","title":"ESM+: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models","date":"2024-07-10","arxiv_id":"2407.07313","repositories_listed":2,"syntology":null},{"url":"/paper/chess-contextual-harnessing-for-efficient-sql","slug":"chess-contextual-harnessing-for-efficient-sql","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","date":"2024-05-27","arxiv_id":"2405.16755","repositories_listed":2,"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/chess-contextual-harnessing-for-efficient-sql#ran","syntology_url":"https://syntology.ai/paper/2405.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16755"}},"official":{"repos":["shayantalaei/chess"],"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/tabsqlify-enhancing-reasoning-capabilities-of","slug":"tabsqlify-enhancing-reasoning-capabilities-of","title":"TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition","date":"2024-04-15","arxiv_id":"2404.10150","repositories_listed":2,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":8,"n_honours":6,"n_violates":0,"n_no_contract":0,"n_pointer_only":15,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/tabsqlify-enhancing-reasoning-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2404.10150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10150"}},"official":{"repos":["mahadi-nahid/tabsqlify"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/can-llms-effectively-leverage-structural","slug":"can-llms-effectively-leverage-structural","title":"Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?","date":"2023-09-28","arxiv_id":"2309.16595","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/can-llms-effectively-leverage-structural#ran","syntology_url":"https://syntology.ai/paper/2309.16595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16595"}},"official":{"repos":["trais-lab/llm-structured-data"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-to-simulate-natural-language","slug":"learning-to-simulate-natural-language","title":"Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing","date":"2023-05-14","arxiv_id":"2305.08195","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-to-simulate-natural-language#ran","syntology_url":"https://syntology.ai/paper/2305.08195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08195"}},"official":{"repos":["hyan5/learning_to_simulate_nl_feedback"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-large-language-models-to-self-debug","slug":"teaching-large-language-models-to-self-debug","title":"Teaching Large Language Models to Self-Debug","date":"2023-04-11","arxiv_id":"2304.05128","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/teaching-large-language-models-to-self-debug#ran","syntology_url":"https://syntology.ai/paper/2304.05128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05128"}},"official":null}},{"url":"/paper/dr-spider-a-diagnostic-evaluation-benchmark","slug":"dr-spider-a-diagnostic-evaluation-benchmark","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","date":"2023-01-21","arxiv_id":"2301.08881","repositories_listed":2,"syntology":null},{"url":"/paper/proton-probing-schema-linking-information","slug":"proton-probing-schema-linking-information","title":"Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing","date":"2022-06-28","arxiv_id":"2206.14017","repositories_listed":2,"syntology":null},{"url":"/paper/mrat-sql-gap-a-portuguese-text-to-sql","slug":"mrat-sql-gap-a-portuguese-text-to-sql","title":"mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformer","date":"2021-10-07","arxiv_id":"2110.03546","repositories_listed":2,"syntology":null},{"url":"/paper/kaggledbqa-realistic-evaluation-of-text-to","slug":"kaggledbqa-realistic-evaluation-of-text-to","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","date":"2021-06-22","arxiv_id":"2106.11455","repositories_listed":2,"syntology":null},{"url":"/paper/unlocking-compositional-generalization-in-pre","slug":"unlocking-compositional-generalization-in-pre","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","date":"2021-04-15","arxiv_id":"2104.07478","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-hybrid-relation-network-for-cross","slug":"dynamic-hybrid-relation-network-for-cross","title":"Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing","date":"2021-01-05","arxiv_id":"2101.01686","repositories_listed":2,"syntology":null},{"url":"/paper/bridging-textual-and-tabular-data-for-cross","slug":"bridging-textual-and-tabular-data-for-cross","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","date":"2020-12-23","arxiv_id":"2012.12627","repositories_listed":2,"syntology":null},{"url":"/paper/igsql-database-schema-interaction-graph-based","slug":"igsql-database-schema-interaction-graph-based","title":"IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation","date":"2020-11-11","arxiv_id":"2011.05744","repositories_listed":2,"syntology":null},{"url":"/paper/seqgensql-a-robust-sequence-generation-model","slug":"seqgensql-a-robust-sequence-generation-model","title":"SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Language","date":"2020-11-07","arxiv_id":"2011.03836","repositories_listed":2,"syntology":null},{"url":"/paper/hybrid-ranking-network-for-text-to-sql","slug":"hybrid-ranking-network-for-text-to-sql","title":"Hybrid Ranking Network for Text-to-SQL","date":"2020-08-11","arxiv_id":"2008.04759","repositories_listed":2,"syntology":null},{"url":"/paper/tableqa-a-large-scale-chinese-text-to-sql","slug":"tableqa-a-large-scale-chinese-text-to-sql","title":"TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation","date":"2020-06-10","arxiv_id":"2006.06434","repositories_listed":2,"syntology":null},{"url":"/paper/valuenet-a-neural-text-to-sql-architecture","slug":"valuenet-a-neural-text-to-sql-architecture","title":"ValueNet: A Natural Language-to-SQL System that Learns from Database Information","date":"2020-05-29","arxiv_id":"2006.00888","repositories_listed":2,"syntology":null},{"url":"/paper/model-based-interactive-semantic-parsing-a","slug":"model-based-interactive-semantic-parsing-a","title":"Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study","date":"2019-10-11","arxiv_id":"1910.05389","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/model-based-interactive-semantic-parsing-a#ran","syntology_url":"https://syntology.ai/paper/1910.05389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05389"}},"official":{"repos":["sunlab-osu/MISP"],"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/a-pilot-study-for-chinese-sql-semantic","slug":"a-pilot-study-for-chinese-sql-semantic","title":"A Pilot Study for Chinese SQL Semantic Parsing","date":"2019-09-29","arxiv_id":"1909.13293","repositories_listed":2,"syntology":null},{"url":"/paper/using-database-rule-for-weak-supervised-text","slug":"using-database-rule-for-weak-supervised-text","title":"Using Database Rule for Weak Supervised Text-to-SQL Generation","date":"2019-07-01","arxiv_id":"1907.00620","repositories_listed":2,"syntology":null},{"url":"/paper/syntaxsqlnet-syntax-tree-networks-for-complex","slug":"syntaxsqlnet-syntax-tree-networks-for-complex","title":"SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task","date":"2018-10-11","arxiv_id":"1810.05237","repositories_listed":2,"syntology":null},{"url":"/paper/schema-r1-a-reasoning-training-approach-for","slug":"schema-r1-a-reasoning-training-approach-for","title":"Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task","date":"2025-06-13","arxiv_id":"2506.11986","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-between-open-source-and","slug":"bridging-the-gap-between-open-source-and","title":"Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA","date":"2025-06-11","arxiv_id":"2506.09657","repositories_listed":1,"syntology":null},{"url":"/paper/seed-enhancing-text-to-sql-performance-and","slug":"seed-enhancing-text-to-sql-performance-and","title":"SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation","date":"2025-06-09","arxiv_id":"2506.07423","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-table-exploring-reinforcement","slug":"reasoning-table-exploring-reinforcement","title":"Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning","date":"2025-06-02","arxiv_id":"2506.01710","repositories_listed":1,"syntology":null},{"url":"/paper/biomedsql-text-to-sql-for-scientific","slug":"biomedsql-text-to-sql-for-scientific","title":"BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases","date":"2025-05-23","arxiv_id":"2505.20321","repositories_listed":1,"syntology":null},{"url":"/paper/arctic-text2sql-r1-simple-rewards-strong","slug":"arctic-text2sql-r1-simple-rewards-strong","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","date":"2025-05-22","arxiv_id":"2505.20315","repositories_listed":1,"syntology":null},{"url":"/paper/exesql-self-taught-text-to-sql-models-with","slug":"exesql-self-taught-text-to-sql-models-with","title":"ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects","date":"2025-05-22","arxiv_id":"2505.17231","repositories_listed":1,"syntology":null},{"url":"/paper/jolt-sql-joint-loss-tuning-of-text-to-sql","slug":"jolt-sql-joint-loss-tuning-of-text-to-sql","title":"JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling","date":"2025-05-20","arxiv_id":"2505.14305","repositories_listed":1,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":6,"n_instrument":10,"n_unverified":2,"n_honours":0,"n_violates":4,"n_no_contract":2,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/jolt-sql-joint-loss-tuning-of-text-to-sql#ran","syntology_url":"https://syntology.ai/paper/2505.14305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14305"}},"official":{"repos":["songjw133/joint-loss-tuning-of-text-to-sql"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/csc-sql-corrective-self-consistency-in-text","slug":"csc-sql-corrective-self-consistency-in-text","title":"CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning","date":"2025-05-19","arxiv_id":"2505.13271","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/csc-sql-corrective-self-consistency-in-text#ran","syntology_url":"https://syntology.ai/paper/2505.13271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13271"}},"official":{"repos":["cycloneboy/csc_sql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graph-reward-sql-execution-free-reinforcement","slug":"graph-reward-sql-execution-free-reinforcement","title":"Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward","date":"2025-05-18","arxiv_id":"2505.12380","repositories_listed":1,"syntology":null},{"url":"/paper/reward-sql-boosting-text-to-sql-via-stepwise","slug":"reward-sql-boosting-text-to-sql-via-stepwise","title":"Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards","date":"2025-05-07","arxiv_id":"2505.04671","repositories_listed":1,"syntology":null},{"url":"/paper/vts-llm-domain-adaptive-llm-agent-for","slug":"vts-llm-domain-adaptive-llm-agent-for","title":"VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language","date":"2025-05-02","arxiv_id":"2505.00989","repositories_listed":1,"syntology":null},{"url":"/paper/when-reasoning-beats-scale-a-1-5b-reasoning","slug":"when-reasoning-beats-scale-a-1-5b-reasoning","title":"When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator","date":"2025-04-30","arxiv_id":"2505.03786","repositories_listed":1,"syntology":null},{"url":"/paper/task-circuit-quantization-leveraging","slug":"task-circuit-quantization-leveraging","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","date":"2025-04-10","arxiv_id":"2504.07389","repositories_listed":1,"syntology":null},{"url":"/paper/elt-bench-an-end-to-end-benchmark-for","slug":"elt-bench-an-end-to-end-benchmark-for","title":"ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines","date":"2025-04-07","arxiv_id":"2504.04808","repositories_listed":1,"syntology":null},{"url":"/paper/sigma-a-dataset-for-text-to-code-semantic","slug":"sigma-a-dataset-for-text-to-code-semantic","title":"Sigma: A dataset for text-to-code semantic parsing with statistical analysis","date":"2025-04-05","arxiv_id":"2504.04301","repositories_listed":1,"syntology":null},{"url":"/paper/excot-optimizing-reasoning-for-text-to-sql","slug":"excot-optimizing-reasoning-for-text-to-sql","title":"ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback","date":"2025-03-25","arxiv_id":"2503.19988","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/excot-optimizing-reasoning-for-text-to-sql#ran","syntology_url":"https://syntology.ai/paper/2503.19988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19988"}},"official":{"repos":["snowflakedb/ArcticTraining"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/linkalign-scalable-schema-linking-for-real","slug":"linkalign-scalable-schema-linking-for-real","title":"LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL","date":"2025-03-24","arxiv_id":"2503.18596","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linkalign-scalable-schema-linking-for-real#ran","syntology_url":"https://syntology.ai/paper/2503.18596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18596"}},"official":{"repos":["Satissss/LinkAlign"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/valid-text-to-sql-generation-with-unification","slug":"valid-text-to-sql-generation-with-unification","title":"Valid Text-to-SQL Generation with Unification-based DeepStochLog","date":"2025-03-17","arxiv_id":"2503.13342","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/valid-text-to-sql-generation-with-unification#ran","syntology_url":"https://syntology.ai/paper/2503.13342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13342"}},"official":{"repos":["ML-KULeuven/deepstochlog-lm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/datrics-text2sql-a-framework-for-natural","slug":"datrics-text2sql-a-framework-for-natural","title":"Datrics Text2SQL. A Framework for Natural Language to SQL Query Generation","date":"2025-03-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/omnisql-synthesizing-high-quality-text-to-sql","slug":"omnisql-synthesizing-high-quality-text-to-sql","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","date":"2025-03-04","arxiv_id":"2503.02240","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/omnisql-synthesizing-high-quality-text-to-sql#ran","syntology_url":"https://syntology.ai/paper/2503.02240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02240"}},"official":{"repos":["RUCKBReasoning/OmniSQL"],"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/automatic-database-description-generation-for","slug":"automatic-database-description-generation-for","title":"Automatic database description generation for Text-to-SQL","date":"2025-02-28","arxiv_id":"2502.20657","repositories_listed":1,"syntology":null},{"url":"/paper/disambiguate-first-parse-later-generating","slug":"disambiguate-first-parse-later-generating","title":"Disambiguate First Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing","date":"2025-02-25","arxiv_id":"2502.18448","repositories_listed":1,"syntology":null},{"url":"/paper/andb-breaking-boundaries-with-an-ai-native","slug":"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/sql-o1-a-self-reward-heuristic-dynamic-search","slug":"sql-o1-a-self-reward-heuristic-dynamic-search","title":"SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL","date":"2025-02-17","arxiv_id":"2502.11741","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sql-o1-a-self-reward-heuristic-dynamic-search#ran","syntology_url":"https://syntology.ai/paper/2502.11741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11741"}},"official":{"repos":["shuailyu0110/sql-o1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uncovering-the-impact-of-chain-of-thought","slug":"uncovering-the-impact-of-chain-of-thought","title":"Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL","date":"2025-02-17","arxiv_id":"2502.11656","repositories_listed":1,"syntology":null},{"url":"/paper/base-sql-a-powerful-open-source-text-to-sql","slug":"base-sql-a-powerful-open-source-text-to-sql","title":"BASE-SQL: A powerful open source Text-To-SQL baseline approach","date":"2025-02-15","arxiv_id":"2502.10739","repositories_listed":1,"syntology":null},{"url":"/paper/cognify-supercharging-gen-ai-workflows-with","slug":"cognify-supercharging-gen-ai-workflows-with","title":"Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning","date":"2025-02-12","arxiv_id":"2502.08056","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/cognify-supercharging-gen-ai-workflows-with#ran","syntology_url":"https://syntology.ai/paper/2502.08056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08056"}},"official":{"repos":["GenseeAI/cognify"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/opengrok-enhancing-sns-data-processing-with","slug":"opengrok-enhancing-sns-data-processing-with","title":"OpenGrok: Enhancing SNS Data Processing with Distilled Knowledge and Mask-like Mechanisms","date":"2025-02-11","arxiv_id":"2502.07312","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-in-context-learning-based-text-to","slug":"a-study-of-in-context-learning-based-text-to","title":"A Study of In-Context-Learning-Based Text-to-SQL Errors","date":"2025-01-16","arxiv_id":"2501.09310","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-estimation-for-error-detection-in","slug":"confidence-estimation-for-error-detection-in","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","date":"2025-01-16","arxiv_id":"2501.09527","repositories_listed":1,"syntology":null},{"url":"/paper/automated-self-refinement-and-self-correction","slug":"automated-self-refinement-and-self-correction","title":"Automated Self-Refinement and Self-Correction for LLM-based Product Attribute Value Extraction","date":"2025-01-02","arxiv_id":"2501.01237","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-multi-modal-data-exploration-in","slug":"explainable-multi-modal-data-exploration-in","title":"Explainable Multi-Modal Data Exploration in Natural Language via LLM Agent","date":"2024-12-24","arxiv_id":"2412.18428","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-and-enhancing-llms-for-multi-turn","slug":"evaluating-and-enhancing-llms-for-multi-turn","title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","date":"2024-12-21","arxiv_id":"2412.17867","repositories_listed":1,"syntology":null},{"url":"/paper/route-robust-multitask-tuning-and","slug":"route-robust-multitask-tuning-and","title":"ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL","date":"2024-12-13","arxiv_id":"2412.10138","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/route-robust-multitask-tuning-and#ran","syntology_url":"https://syntology.ai/paper/2412.10138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10138"}},"official":{"repos":["alibaba/route"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-prior-experience-an-expandable","slug":"leveraging-prior-experience-an-expandable","title":"Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL","date":"2024-11-20","arxiv_id":"2411.13244","repositories_listed":1,"syntology":null},{"url":"/paper/suffixdecoding-a-model-free-approach-to","slug":"suffixdecoding-a-model-free-approach-to","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","date":"2024-11-07","arxiv_id":"2411.04975","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suffixdecoding-a-model-free-approach-to#ran","syntology_url":"https://syntology.ai/paper/2411.04975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04975"}},"official":{"repos":["snowflakedb/arcticinference"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rsl-sql-robust-schema-linking-in-text-to-sql","slug":"rsl-sql-robust-schema-linking-in-text-to-sql","title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","date":"2024-10-31","arxiv_id":"2411.00073","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":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/rsl-sql-robust-schema-linking-in-text-to-sql#ran","syntology_url":"https://syntology.ai/paper/2411.00073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00073"}},"official":{"repos":["laqcce-cao/rsl-sql"],"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/msc-sql-multi-sample-critiquing-small","slug":"msc-sql-multi-sample-critiquing-small","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","date":"2024-10-16","arxiv_id":"2410.12916","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/msc-sql-multi-sample-critiquing-small#ran","syntology_url":"https://syntology.ai/paper/2410.12916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12916"}},"official":{"repos":["layer6ai-labs/msc-sql"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/e-sql-direct-schema-linking-via-question","slug":"e-sql-direct-schema-linking-via-question","title":"E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL","date":"2024-09-25","arxiv_id":"2409.16751","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/e-sql-direct-schema-linking-via-question#ran","syntology_url":"https://syntology.ai/paper/2409.16751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16751"}},"official":{"repos":["HasanAlpCaferoglu/E-SQL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/syntqa-synergistic-table-based-question","slug":"syntqa-synergistic-table-based-question","title":"SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA","date":"2024-09-25","arxiv_id":"2409.16682","repositories_listed":1,"syntology":null},{"url":"/paper/flex-expert-level-false-less-execution-metric","slug":"flex-expert-level-false-less-execution-metric","title":"FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark","date":"2024-09-24","arxiv_id":"2409.19014","repositories_listed":1,"syntology":null},{"url":"/paper/2409-14082","slug":"2409-14082","title":"PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL","date":"2024-09-21","arxiv_id":"2409.14082","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2409-14082#ran","syntology_url":"https://syntology.ai/paper/2409.14082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14082"}},"official":{"repos":["lrlbbzl/ptd-sql"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-good-multi-lingual","slug":"large-language-models-are-good-multi-lingual","title":"Large Language Models are Good Multi-lingual Learners : When LLMs Meet Cross-lingual Prompts","date":"2024-09-17","arxiv_id":"2409.11056","repositories_listed":1,"syntology":null},{"url":"/paper/select-sql-self-correcting-ensemble-chain-of","slug":"select-sql-self-correcting-ensemble-chain-of","title":"SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL","date":"2024-09-16","arxiv_id":"2409.10007","repositories_listed":1,"syntology":null},{"url":"/paper/text2sql-is-not-enough-unifying-ai-and","slug":"text2sql-is-not-enough-unifying-ai-and","title":"Text2SQL is Not Enough: Unifying AI and Databases with TAG","date":"2024-08-27","arxiv_id":"2408.14717","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/text2sql-is-not-enough-unifying-ai-and#ran","syntology_url":"https://syntology.ai/paper/2408.14717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14717"}},"official":{"repos":["tag-research/tag-bench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dac-decomposed-automation-correction-for-text","slug":"dac-decomposed-automation-correction-for-text","title":"DAC: Decomposed Automation Correction for Text-to-SQL","date":"2024-08-16","arxiv_id":"2408.08779","repositories_listed":1,"syntology":null},{"url":"/paper/mag-sql-multi-agent-generative-approach-with","slug":"mag-sql-multi-agent-generative-approach-with","title":"MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL","date":"2024-08-15","arxiv_id":"2408.07930","repositories_listed":1,"syntology":{"n":25,"n_ran":21,"n_constructed":0,"n_ran_checked":12,"n_instrument":9,"n_unverified":4,"n_honours":3,"n_violates":9,"n_no_contract":0,"n_pointer_only":4,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 9 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mag-sql-multi-agent-generative-approach-with#ran","syntology_url":"https://syntology.ai/paper/2408.07930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07930"}},"official":{"repos":["LancelotXWX/MAG-SQL"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-of-nl2sql-with-large-language-models","slug":"a-survey-of-nl2sql-with-large-language-models","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","date":"2024-08-09","arxiv_id":"2408.05109","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/a-survey-of-nl2sql-with-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2408.05109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05109"}},"official":{"repos":["hkustdial/nl2sql_handbook"],"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/i-need-help-evaluating-llm-s-ability-to-ask","slug":"i-need-help-evaluating-llm-s-ability-to-ask","title":"I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation","date":"2024-07-20","arxiv_id":"2407.14767","repositories_listed":1,"syntology":null},{"url":"/paper/ambrosia-a-benchmark-for-parsing-ambiguous","slug":"ambrosia-a-benchmark-for-parsing-ambiguous","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","date":"2024-06-27","arxiv_id":"2406.19073","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ambrosia-a-benchmark-for-parsing-ambiguous#ran","syntology_url":"https://syntology.ai/paper/2406.19073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19073"}},"official":{"repos":["saparina/ambrosia"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sqlfixagent-towards-semantic-accurate-sql","slug":"sqlfixagent-towards-semantic-accurate-sql","title":"SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration","date":"2024-06-19","arxiv_id":"2406.13408","repositories_listed":1,"syntology":null},{"url":"/paper/magic-generating-self-correction-guideline","slug":"magic-generating-self-correction-guideline","title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","date":"2024-06-18","arxiv_id":"2406.12692","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magic-generating-self-correction-guideline#ran","syntology_url":"https://syntology.ai/paper/2406.12692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12692"}},"official":{"repos":["microsoft/synqo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/qda-sql-questions-enhanced-dialogue","slug":"qda-sql-questions-enhanced-dialogue","title":"QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL","date":"2024-06-15","arxiv_id":"2406.10593","repositories_listed":1,"syntology":null},{"url":"/paper/booksql-a-large-scale-text-to-sql-dataset-for","slug":"booksql-a-large-scale-text-to-sql-dataset-for","title":"BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain","date":"2024-06-12","arxiv_id":"2406.07860","repositories_listed":1,"syntology":null},{"url":"/paper/before-generation-align-it-a-novel-and","slug":"before-generation-align-it-a-novel-and","title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","date":"2024-05-24","arxiv_id":"2405.15307","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/before-generation-align-it-a-novel-and#ran","syntology_url":"https://syntology.ai/paper/2405.15307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15307"}},"official":{"repos":["quge2023/TA-SQL"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ehr-seqsql-a-sequential-text-to-sql-dataset","slug":"ehr-seqsql-a-sequential-text-to-sql-dataset","title":"EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records","date":"2024-05-23","arxiv_id":"2406.00019","repositories_listed":1,"syntology":null},{"url":"/paper/coe-sql-in-context-learning-for-multi-turn","slug":"coe-sql-in-context-learning-for-multi-turn","title":"CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions","date":"2024-05-04","arxiv_id":"2405.02712","repositories_listed":1,"syntology":null},{"url":"/paper/overview-of-the-ehrsql-2024-shared-task-on","slug":"overview-of-the-ehrsql-2024-shared-task-on","title":"Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Records","date":"2024-05-04","arxiv_id":"2405.06673","repositories_listed":1,"syntology":null},{"url":"/paper/probgate-at-ehrsql-2024-enhancing-sql-query","slug":"probgate-at-ehrsql-2024-enhancing-sql-query","title":"ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handling","date":"2024-04-25","arxiv_id":"2404.16659","repositories_listed":1,"syntology":null},{"url":"/paper/dubo-sql-diverse-retrieval-augmented","slug":"dubo-sql-diverse-retrieval-augmented","title":"Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL","date":"2024-04-19","arxiv_id":"2404.12560","repositories_listed":1,"syntology":null}],"syntology_records":37,"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":70,"papers_where_code_ran_first_page":"/task/text-to-sql/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":5,"url":"/task/text-to-sql/papers/2","json":"/task/text-to-sql/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/text-to-sql/papers/3","json":"/task/text-to-sql/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/text-to-sql/papers/4","json":"/task/text-to-sql/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/text-to-sql/papers/5","json":"/task/text-to-sql/papers/5.json","rows":24},{"order":"ran","page":1,"of":1,"url":"/task/text-to-sql/papers/ran/1","json":"/task/text-to-sql/papers/ran/1.json","rows":70}],"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":"55c6fb5fd80425e2d5d10864d6c47e067048efa65f7423be2a088360e81c55c2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}