{"task":"Text-To-SQL","dataset":"spider","metric_names":["Execution Accuracy (Test)","Exact Match Accuracy (Test)","Execution Accuracy (Dev)","Exact Match Accuracy (Dev)"],"rows":[{"id":758738,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"AttnLink","metrics":{"Execution Accuracy (Test)":"95.95"},"paper_url":"https://paperswithcode.com/paper/attnlink-turning-attention-into-schema-links-for-text-to-sql","paper_title":"AttnLink: Turning Attention into Schema Links for Text-to-SQL","paper_date":"2026-08-01","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":758846,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"SIRIUS-SQL","metrics":{"Execution Accuracy (Test)":"91.20"},"paper_url":"https://paperswithcode.com/paper/sirius-sql-anchoring-multi-candidate-text-to-sql-in-execution-feedback","paper_title":"SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback","paper_date":"2026-05-31","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759179,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"AutoLink","metrics":{"Execution Accuracy (Test)":"91.2"},"paper_url":"https://paperswithcode.com/paper/autolink-autonomous-schema-exploration-and-expansion-for-scalable-schema-linking-in-text-to-sql-at-scale","paper_title":"AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale","paper_date":"2025-11-21","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":758737,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"SERL-SQL","metrics":{"Execution Accuracy (Test)":"89.92"},"paper_url":"https://paperswithcode.com/paper/serl-sql-selective-hindsight-distillation-for-text-to-sql-reinforcement-agentic-learning","paper_title":"SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning","paper_date":"2026-08-01","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759215,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"MARS-SQL","metrics":{"Execution Accuracy (Test)":"89.75"},"paper_url":"https://paperswithcode.com/paper/mars-sql-a-multi-agent-reinforcement-learning-framework-for-text-to-sql","paper_title":"MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL","paper_date":"2025-11-02","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":40783,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"XiYan-SQL","metrics":{"Execution Accuracy (Test)":"89.65"},"paper_url":"https://arxiv.org/abs/2411.08599v3","paper_title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","paper_date":"2024-11-13","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"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758749,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"Policy-Conditioned Constrained Decoding ","metrics":{"Execution Accuracy (Test)":"88.7"},"paper_url":"https://paperswithcode.com/paper/policy-conditioned-constrained-decoding-for-column-level-access-control-in-text-to-sql","paper_title":"Policy-Conditioned Constrained Decoding for Column-Level Access Control in Text-to-SQL","paper_date":"2026-07-14","code_links":[{"title":"arXivSub_daily_arxiv","url":"https://github.com/arxivsub/arXivSub_daily_arxiv"}],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759261,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"LitE-SQL","metrics":{"Execution Accuracy (Test)":"88.45"},"paper_url":"https://paperswithcode.com/paper/lite-sql-a-lightweight-and-efficient-text-to-sql-framework-with-vector-based-schema-linking-and-execution-guided-self-correction","paper_title":"LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction","paper_date":"2025-10-10","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":758801,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"DecoSearch","metrics":{"Execution Accuracy (Test)":"88.31"},"paper_url":"https://paperswithcode.com/paper/decosearch-complexity-aware-routing-and-plan-level-repair-for-text-to-sql","paper_title":"DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL","paper_date":"2026-06-16","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":40784,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"PET-SQL","metrics":{"Exact Match Accuracy (Test)":"66.6","Execution Accuracy (Test)":"87.6"},"paper_url":"https://arxiv.org/abs/2403.09732v4","paper_title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","paper_date":"2024-03-13","code_links":[{"title":"zhshlii/petsql","url":"https://github.com/zhshlii/petsql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758830,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"ZAS-SQL","metrics":{"Execution Accuracy (Test)":"87.2"},"paper_url":"https://paperswithcode.com/paper/zas-sql-distilling-rules-from-failures-for-zero-shot-text-to-sql","paper_title":"ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL","paper_date":"2026-06-06","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":40785,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"DAIL-SQL + GPT-4 + Self-Consistency","metrics":{"Exact Match Accuracy (Dev)":"74.4","Execution Accuracy (Dev)":"84.4","Execution Accuracy (Test)":"86.6"},"paper_url":"https://arxiv.org/abs/2308.15363v4","paper_title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","paper_date":"2023-08-29","code_links":[{"title":"beachwang/dail-sql","url":"https://github.com/beachwang/dail-sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":759255,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"AGENTIQL","metrics":{"Execution Accuracy (Test)":"86.07"},"paper_url":"https://paperswithcode.com/paper/agentiql-an-agent-inspired-multi-expert-framework-for-text-to-sql-generation","paper_title":"AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation","paper_date":"2025-10-12","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":758951,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"AV-SQL","metrics":{"Execution Accuracy (Test)":"85.59"},"paper_url":"https://paperswithcode.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views","paper_title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","paper_date":"2026-04-08","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759088,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"Single-Agent","metrics":{"Execution Accuracy (Test)":"85.5"},"paper_url":"https://paperswithcode.com/paper/llm-based-sql-generation-prompting-self-refinement-and-adaptive-weighted-majority-voting","paper_title":"LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting","paper_date":"2026-01-25","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":40786,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"DIN-SQL + GPT-4","metrics":{"Exact Match Accuracy (Test)":"60","Execution Accuracy (Test)":"85.3"},"paper_url":"https://arxiv.org/abs/2304.11015v3","paper_title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","paper_date":"2023-04-21","code_links":[{"title":"mohammadrezapourreza/few-shot-nl2sql-with-prompting","url":"https://github.com/mohammadrezapourreza/few-shot-nl2sql-with-prompting"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":759317,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"X-Linking","metrics":{"Execution Accuracy (Test)":"84.9"},"paper_url":"https://paperswithcode.com/paper/x-sql-expert-schema-linking-and-understanding-of-text-to-sql-with-multi-llms","paper_title":"X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs","paper_date":"2025-09-07","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":40787,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"MSc-SQL","metrics":{"Execution Accuracy (Test)":"84.7"},"paper_url":"https://arxiv.org/abs/2410.12916v1","paper_title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","paper_date":"2024-10-16","code_links":[{"title":"layer6ai-labs/msc-sql","url":"https://github.com/layer6ai-labs/msc-sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40788,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"MARLO + Claude 2.1","metrics":{"Execution Accuracy (Dev)":"83.6","Execution Accuracy (Test)":"84.0"},"paper_url":"https://arxiv.org/abs/2410.14049v1","paper_title":"Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection","paper_date":"2024-10-17","code_links":[],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40789,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"C3 + ChatGPT + Zero-Shot","metrics":{"Execution Accuracy (Dev)":"81.8","Execution Accuracy (Test)":"82.3"},"paper_url":"https://arxiv.org/abs/2307.07306v1","paper_title":"C3: Zero-shot Text-to-SQL with ChatGPT","paper_date":"2023-07-14","code_links":[{"title":"bigbigwatermalon/c3sql","url":"https://github.com/bigbigwatermalon/c3sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40790,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"RESDSQL-3B + NatSQL","metrics":{"Exact Match Accuracy (Dev)":"80.5","Exact Match Accuracy (Test)":"72.0","Execution Accuracy (Dev)":"84.1","Execution Accuracy (Test)":"79.9"},"paper_url":"https://arxiv.org/abs/2302.05965v3","paper_title":"RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL","paper_date":"2023-02-12","code_links":[{"title":"ruckbreasoning/resdsql","url":"https://github.com/ruckbreasoning/resdsql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758809,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"CoTE-SQL","metrics":{"Execution Accuracy (Test)":"79.60"},"paper_url":"https://paperswithcode.com/paper/integrating-reasoning-and-generalization-in-text-to-sql-via-self-enhanced-fine-tuning","paper_title":"Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning","paper_date":"2026-06-14","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":40791,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"T5-3B+NatSQL+Token Preprocessing","metrics":{"Exact Match Accuracy (Dev)":"69.4","Execution Accuracy (Dev)":"73.7","Execution Accuracy (Test)":"78"},"paper_url":"https://arxiv.org/abs/2305.17378v1","paper_title":"Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques","paper_date":"2023-05-27","code_links":[{"title":"dakingrai/ood-generalization-semantic-boundary-techniques","url":"https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40792,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"Graphix-3B+PICARD","metrics":{"Exact Match Accuracy (Dev)":"77.1","Execution Accuracy (Dev)":"81.0","Execution Accuracy (Test)":"77.6"},"paper_url":"https://arxiv.org/abs/2301.07507v1","paper_title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","paper_date":"2023-01-18","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/graphix"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40793,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"T5-SR","metrics":{"Exact Match Accuracy (Dev)":"77.2","Exact Match Accuracy (Test)":"72.4","Execution Accuracy (Test)":"75.2"},"paper_url":"https://arxiv.org/abs/2306.08368v1","paper_title":"T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing","paper_date":"2023-06-14","code_links":[{"title":"JuruoMP/T5-SR","url":"https://github.com/JuruoMP/T5-SR"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40794,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"T5-3B + PICARD","metrics":{"Exact Match Accuracy (Dev)":"75.5","Exact Match Accuracy (Test)":"71.9 ","Execution Accuracy (Test)":"75.1"},"paper_url":"https://arxiv.org/abs/2109.05093v1","paper_title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","paper_date":"2021-09-10","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"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40795,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"SADGA + GAP","metrics":{"Exact Match Accuracy (Dev)":"73.1","Exact Match Accuracy (Test)":"70.1"},"paper_url":"https://arxiv.org/abs/2111.00653v3","paper_title":"SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL","paper_date":"2021-11-01","code_links":[{"title":"dmirlab-group/sadga","url":"https://github.com/dmirlab-group/sadga"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40796,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"RYANSQL (BERT)","metrics":{"Exact Match Accuracy (Dev)":"66.6","Exact Match Accuracy (Test)":"58.2"},"paper_url":"https://arxiv.org/abs/2004.03125v1","paper_title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","paper_date":"2020-04-07","code_links":[{"title":"kakaoenterprise/RYANSQL","url":"https://github.com/kakaoenterprise/RYANSQL"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40797,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"datagpt-sql-7B + InvalidSQL-Feedback","metrics":{"Exact Match Accuracy (Dev)":"81.6","Execution Accuracy (Dev)":"87.2"},"paper_url":"https://arxiv.org/abs/2409.15985v1","paper_title":"DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":40798,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"datagpt-sql-7B","metrics":{"Exact Match Accuracy (Dev)":"80.3","Execution Accuracy (Dev)":"84.8"},"paper_url":"https://arxiv.org/abs/2409.15985v1","paper_title":"DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":40799,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"code-davinci-002 175B (LEVER)","metrics":{"Execution Accuracy (Dev)":"81.9"},"paper_url":"https://arxiv.org/abs/2302.08468v3","paper_title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","paper_date":"2023-02-16","code_links":[{"title":"niansong1996/lever","url":"https://github.com/niansong1996/lever"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40800,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"DELLM + GPT-4","metrics":{"Execution Accuracy (Dev)":"71.68"},"paper_url":"https://arxiv.org/abs/2402.11517v3","paper_title":"Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM","paper_date":"2024-02-18","code_links":[{"title":"Rcrossmeister/Knowledge-to-SQL","url":"https://github.com/Rcrossmeister/Knowledge-to-SQL"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40801,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"RATSQL + GAP","metrics":{"Exact Match Accuracy (Dev)":"71.8"},"paper_url":"https://arxiv.org/abs/2012.10309v1","paper_title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","paper_date":"2020-12-18","code_links":[{"title":"awslabs/gap-text2sql","url":"https://github.com/awslabs/gap-text2sql"},{"title":"dmirlab-group/sadga","url":"https://github.com/dmirlab-group/sadga"},{"title":"c4ai/gap-text2sql","url":"https://github.com/c4ai/gap-text2sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":40802,"task":"Text-To-SQL","parent_task":"Semantic Parsing","dataset":"spider","model_name":"MAPO + TABERTLarge (K = 3)","metrics":{"Exact Match Accuracy (Dev)":"64.5"},"paper_url":"https://arxiv.org/abs/2005.08314v1","paper_title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","paper_date":"2020-05-17","code_links":[{"title":"facebookresearch/tabert","url":"https://github.com/facebookresearch/tabert"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93808,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"XiYan-SQL","metrics":{"Execution Accuracy (Test)":"89.65"},"paper_url":"https://arxiv.org/abs/2411.08599v3","paper_title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","paper_date":"2024-11-13","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"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93809,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"PET-SQL","metrics":{"Exact Match Accuracy (Test)":"66.6","Execution Accuracy (Test)":"87.6"},"paper_url":"https://arxiv.org/abs/2403.09732v4","paper_title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","paper_date":"2024-03-13","code_links":[{"title":"zhshlii/petsql","url":"https://github.com/zhshlii/petsql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93810,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"DAIL-SQL + GPT-4 + Self-Consistency","metrics":{"Exact Match Accuracy (Dev)":"74.4","Execution Accuracy (Dev)":"84.4","Execution Accuracy (Test)":"86.6"},"paper_url":"https://arxiv.org/abs/2308.15363v4","paper_title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","paper_date":"2023-08-29","code_links":[{"title":"beachwang/dail-sql","url":"https://github.com/beachwang/dail-sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93811,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"DIN-SQL + GPT-4","metrics":{"Exact Match Accuracy (Test)":"60","Execution Accuracy (Test)":"85.3"},"paper_url":"https://arxiv.org/abs/2304.11015v3","paper_title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","paper_date":"2023-04-21","code_links":[{"title":"mohammadrezapourreza/few-shot-nl2sql-with-prompting","url":"https://github.com/mohammadrezapourreza/few-shot-nl2sql-with-prompting"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93812,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"MSc-SQL","metrics":{"Execution Accuracy (Test)":"84.7"},"paper_url":"https://arxiv.org/abs/2410.12916v1","paper_title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","paper_date":"2024-10-16","code_links":[{"title":"layer6ai-labs/msc-sql","url":"https://github.com/layer6ai-labs/msc-sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93813,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"MARLO + Claude 2.1","metrics":{"Execution Accuracy (Dev)":"83.6","Execution Accuracy (Test)":"84.0"},"paper_url":"https://arxiv.org/abs/2410.14049v1","paper_title":"Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection","paper_date":"2024-10-17","code_links":[],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93814,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"C3 + ChatGPT + Zero-Shot","metrics":{"Execution Accuracy (Dev)":"81.8","Execution Accuracy (Test)":"82.3"},"paper_url":"https://arxiv.org/abs/2307.07306v1","paper_title":"C3: Zero-shot Text-to-SQL with ChatGPT","paper_date":"2023-07-14","code_links":[{"title":"bigbigwatermalon/c3sql","url":"https://github.com/bigbigwatermalon/c3sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93815,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"RESDSQL-3B + NatSQL","metrics":{"Exact Match Accuracy (Dev)":"80.5","Exact Match Accuracy (Test)":"72.0","Execution Accuracy (Dev)":"84.1","Execution Accuracy (Test)":"79.9"},"paper_url":"https://arxiv.org/abs/2302.05965v3","paper_title":"RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL","paper_date":"2023-02-12","code_links":[{"title":"ruckbreasoning/resdsql","url":"https://github.com/ruckbreasoning/resdsql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93816,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"T5-3B+NatSQL+Token Preprocessing","metrics":{"Exact Match Accuracy (Dev)":"69.4","Execution Accuracy (Dev)":"73.7","Execution Accuracy (Test)":"78"},"paper_url":"https://arxiv.org/abs/2305.17378v1","paper_title":"Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques","paper_date":"2023-05-27","code_links":[{"title":"dakingrai/ood-generalization-semantic-boundary-techniques","url":"https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93817,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"Graphix-3B+PICARD","metrics":{"Exact Match Accuracy (Dev)":"77.1","Execution Accuracy (Dev)":"81.0","Execution Accuracy (Test)":"77.6"},"paper_url":"https://arxiv.org/abs/2301.07507v1","paper_title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","paper_date":"2023-01-18","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/graphix"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93818,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"T5-SR","metrics":{"Exact Match Accuracy (Dev)":"77.2","Exact Match Accuracy (Test)":"72.4","Execution Accuracy (Test)":"75.2"},"paper_url":"https://arxiv.org/abs/2306.08368v1","paper_title":"T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing","paper_date":"2023-06-14","code_links":[{"title":"JuruoMP/T5-SR","url":"https://github.com/JuruoMP/T5-SR"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93819,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"T5-3B + PICARD","metrics":{"Exact Match Accuracy (Dev)":"75.5","Exact Match Accuracy (Test)":"71.9 ","Execution Accuracy (Test)":"75.1"},"paper_url":"https://arxiv.org/abs/2109.05093v1","paper_title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","paper_date":"2021-09-10","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"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93820,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"SADGA + GAP","metrics":{"Exact Match Accuracy (Dev)":"73.1","Exact Match Accuracy (Test)":"70.1"},"paper_url":"https://arxiv.org/abs/2111.00653v3","paper_title":"SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL","paper_date":"2021-11-01","code_links":[{"title":"dmirlab-group/sadga","url":"https://github.com/dmirlab-group/sadga"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93821,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"RYANSQL (BERT)","metrics":{"Exact Match Accuracy (Dev)":"66.6","Exact Match Accuracy (Test)":"58.2"},"paper_url":"https://arxiv.org/abs/2004.03125v1","paper_title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","paper_date":"2020-04-07","code_links":[{"title":"kakaoenterprise/RYANSQL","url":"https://github.com/kakaoenterprise/RYANSQL"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93822,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"datagpt-sql-7B + InvalidSQL-Feedback","metrics":{"Exact Match Accuracy (Dev)":"81.6","Execution Accuracy (Dev)":"87.2"},"paper_url":"https://arxiv.org/abs/2409.15985v1","paper_title":"DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":93823,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"datagpt-sql-7B","metrics":{"Exact Match Accuracy (Dev)":"80.3","Execution Accuracy (Dev)":"84.8"},"paper_url":"https://arxiv.org/abs/2409.15985v1","paper_title":"DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":93824,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"code-davinci-002 175B (LEVER)","metrics":{"Execution Accuracy (Dev)":"81.9"},"paper_url":"https://arxiv.org/abs/2302.08468v3","paper_title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","paper_date":"2023-02-16","code_links":[{"title":"niansong1996/lever","url":"https://github.com/niansong1996/lever"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93825,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"DELLM + GPT-4","metrics":{"Execution Accuracy (Dev)":"71.68"},"paper_url":"https://arxiv.org/abs/2402.11517v3","paper_title":"Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM","paper_date":"2024-02-18","code_links":[{"title":"Rcrossmeister/Knowledge-to-SQL","url":"https://github.com/Rcrossmeister/Knowledge-to-SQL"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93826,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"RATSQL + GAP","metrics":{"Exact Match Accuracy (Dev)":"71.8"},"paper_url":"https://arxiv.org/abs/2012.10309v1","paper_title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","paper_date":"2020-12-18","code_links":[{"title":"awslabs/gap-text2sql","url":"https://github.com/awslabs/gap-text2sql"},{"title":"dmirlab-group/sadga","url":"https://github.com/dmirlab-group/sadga"},{"title":"c4ai/gap-text2sql","url":"https://github.com/c4ai/gap-text2sql"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":93827,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"MAPO + TABERTLarge (K = 3)","metrics":{"Exact Match Accuracy (Dev)":"64.5"},"paper_url":"https://arxiv.org/abs/2005.08314v1","paper_title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","paper_date":"2020-05-17","code_links":[{"title":"facebookresearch/tabert","url":"https://github.com/facebookresearch/tabert"}],"metrics_order":"[\"Execution Accuracy (Test)\", \"Exact Match Accuracy (Test)\", \"Execution Accuracy (Dev)\", \"Exact Match Accuracy (Dev)\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758733,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"MERIT","metrics":{"Execution Accuracy (Test)":"69.79"},"paper_url":"https://paperswithcode.com/paper/causal-episodic-memory-for-feedback-driven-agent-repair","paper_title":"Causal Episodic Memory for Feedback-Driven Agent Repair","paper_date":"2026-08-06","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759170,"task":"Text-To-SQL","parent_task":null,"dataset":"spider","model_name":"DSR-SQL","metrics":{"Execution Accuracy (Test)":"68.32"},"paper_url":"https://paperswithcode.com/paper/text-to-sql-as-dual-state-reasoning-integrating-adaptive-context-and-progressive-generation","paper_title":"Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation","paper_date":"2025-11-26","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}