mlsanityData to 14 Oct 2026

SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL

arXiv 2506.00391 ↗First posted 31 May 2025cs.CLcited by 16

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

Abstract (arXiv)

Current self-correction approaches in text-to-SQL face two critical limitations: 1) Conventional self-correction methods rely on recursive self-calls of LLMs, resulting in multiplicative computational overhead, and 2) LLMs struggle to implement effective error detection and correction for declarative SQL queries, as they fail to demonstrate the underlying reasoning path. In this work, we propose SHARE, an SLM-based Hierarchical Action corREction assistant that enables LLMs to perform more precise error localization and efficient correction. SHARE orchestrates three specialized Small Language Models (SLMs) in a sequential pipeline, where it first transforms declarative SQL queries into stepwise action trajectories that reveal underlying reasoning, followed by a two-phase granular refinement. We further propose a novel hierarchical self-evolution strategy for data-efficient training. Experimental results demonstrate that SHARE effectively enhances self-correction capabilities while proving robust across various LLMs. Furthermore, our comprehensive analysis shows that SHARE maintains strong performance even in low-resource training settings, which is particularly valuable for text-to-SQL applications with data privacy constraints.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 38 of its 49 references that are in the map. First posted on arXiv 31 May 2025.

Builds on

38 of 49 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL2 Oct
  2. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm16 Feb
  3. 2024A Survey of Table Reasoning with Large Language Models13 Feb

Other references · 35

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  6. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  9. 2023Teaching Large Language Models to Self-Debugcited by 988
  10. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  11. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  12. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 505
23 more
  1. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  2. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  3. 2022CodeT: Code Generation with Generated Testscited by 384
  4. 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Studycited by 262
  5. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  6. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  7. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  8. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 105
  9. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 95
  10. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  11. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  12. 2025ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generationcited by 92
  13. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 50
  14. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  15. 2024MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLcited by 35
  16. 2022UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLcited by 20
  17. 2024Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agentscited by 17
  18. 2024SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmarkcited by 14
  19. 2022Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQLcited by 12
  20. 2024Using LLM to select the right SQL Query from candidatescited by 12
  21. 2024Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignmentcited by 11
  22. 2024EPI-SQL: Enhancing Text-to-SQL Translation with Error-Prevention Instructionscited by 8
  23. 2024R3: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Taskscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 12.

16 papers.

Sort:

By area:

  1. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 19
  2. 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applicationscited by 16
  3. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 15
  4. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generationcited by 10
  5. 2026Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQLcited by 4
  6. 2026ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinementcited by 2
  7. 2026Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineeringcited by 1
  8. 2026EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinementcited by 1
  9. 2026SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesiscited by 0
  10. 2026LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Predictioncited by 0
  11. 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQLcited by 0
  12. 2026Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQLcited by 0
4 more
  1. 2026Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQLcited by 0
  2. 2026BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotationscited by 0
  3. 2026COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Trainingcited by 0
  4. 2026Why, Where, How: Taxonomy-guided Error Grounding for Code Repair in NL2SQLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models
  2. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
  3. 2025SQLCritic: Correcting Text-to-SQL Generation via Clause-wise Critic
  4. 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning
  5. 2025RetrySQL: text-to-SQL training with retry data for self-correcting query generation
  6. 2024Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios
  7. 2025SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning
  8. 2025SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction