mlsanityData to 7 Oct 2026

N-Best Hypotheses Reranking for Text-To-SQL Systems

arXiv 2210.10668 ↗First posted 19 Oct 2022cs.CL cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL task maps natural language utterances to structured queries that can be issued to a database. State-of-the-art (SOTA) systems rely on finetuning large, pre-trained language models in conjunction with constrained decoding applying a SQL parser. On the well established Spider dataset, we begin with Oracle studies: specifically, choosing an Oracle hypothesis from a SOTA model's 10-best list, yields a 7.7% absolute improvement in both exact match (EM) and execution (EX) accuracy, showing significant potential improvements with reranking. Identifying coherence and correctness as reranking approaches, we design a model generating a query plan and propose a heuristic schema linking algorithm. Combining both approaches, with T5-Large, we obtain a consistent 1% improvement in EM accuracy, and a ~2.5% improvement in EX, establishing a new SOTA for this task. Our comprehensive error studies on DEV data show the underlying difficulty in making progress on this task.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

27 of 45 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  8. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  9. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  10. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  11. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  12. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
15 more
  1. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  2. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  3. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  4. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  5. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
  6. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
  7. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  8. 2018TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generationcited by 81
  9. 2021Language Model Evaluation Beyond Perplexitycited by 77
  10. 2019Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsingcited by 74
  11. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  12. 2021Coherence boosting: When your pretrained language model is not paying enough attentioncited by 38
  13. 2021ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parsercited by 35
  14. 2020Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-rankercited by 12
  15. 2020SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Languagecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 6; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Teaching Large Language Models to Self-Debugcited by 963
  2. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  3. 2023Universal Self-Consistency for Large Language Model Generationcited by 198
  4. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  5. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  6. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  7. 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34
  8. 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 31
  9. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
  10. 2024Using LLM to select the right SQL Query from candidatescited by 12
  11. 2024Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queriescited by 12
  12. 2025Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrievalcited by 3
7 more
  1. 2025End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generationcited by 2
  2. 2023Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Aheadcited by 0
  3. 2023Translating Natural Language Queries to SQL Using the T5 Modelcited by 0
  4. 2025StreamLink: Large-Language-Model Driven Distributed Data Engineering Systemcited by 0
  5. 2025Text to Query Plans for Question Answering on Large Tablescited by 0
  6. 2025DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Datacited by 0
  7. 2026The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactionscited by 0