mlsanityData to 7 Oct 2026

Multi-Turn Interactions for Text-to-SQL with Large Language Models

arXiv 2408.11062 ↗First posted 9 Aug 2024cs.CL cs.AIcited by 2

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

This study explores text-to-SQL parsing by leveraging the powerful reasoning capabilities of large language models (LLMs). Despite recent advancements, existing LLM-based methods are still inefficient and struggle to handle cases with wide tables effectively. Furthermore, current interaction-based approaches either lack a step-by-step, interpretable SQL generation process or fail to provide a universally applicable interaction design. To address these challenges, we introduce Interactive-T2S, a framework that generates SQL queries through direct interactions with databases. This framework includes four general tools that facilitate proactive and efficient information retrieval by the LLM. Additionally, we have developed detailed exemplars to demonstrate the step-wise reasoning processes within our framework. Our approach achieves advanced performance on the Spider and BIRD datasets as well as their variants. Notably, we obtain state-of-the-art results on the BIRD leaderboard under the setting without oracle knowledge, demonstrating the effectiveness of our method.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 28 of its 39 references that are in the map. First posted on arXiv 9 Aug 2024.

Builds on

28 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought26 Oct

Other references · 27

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  3. 2023Teaching Large Language Models to Self-Debugcited by 963
  4. 2022A Survey on In-context Learningcited by 717
  5. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  6. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  7. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  8. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  9. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  10. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  11. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  12. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
15 more
  1. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  2. 2022Natural Language to Code Translation with Executioncited by 122
  3. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  4. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  5. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  6. 2024Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumptioncited by 96
  7. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  8. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  9. 2023SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)cited by 42
  10. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  11. 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34
  12. 2024Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmarkcited by 33
  13. 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencycited by 26
  14. 2024Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Modelscited by 25
  15. 2023Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chaincited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQLcited by 19
  2. 2026Arming Data Agents with Tribal Knowledgecited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2025RAISE: Reasoning Agent for Interactive SQL Exploration
  2. 2025Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
  3. 2024Lucy: Think and Reason to Solve Text-to-SQL
  4. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions
  5. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
  6. 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
  7. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
  8. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems