Why, Where, How: Taxonomy-guided Error Grounding for Code Repair in NL2SQL

arXiv:2610.05060 · cs.AI · Submitted 2026-10-04 · Read on arXiv

cs.AI

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: 32 pages

Code: https://github.com/isuchan0212/why-where-how

Project page: http://stackoverflow.com

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 1× in this paper · explained in 3 episodes

Sources

• SantaCoder: don't reach for the stars!
• SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction
• Evaluating Large Language Models Trained on Code
• A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?
• C3: Zero-shot Text-to-SQL with ChatGPT
• InCoder: A Generative Model for Code Infilling and Synthesis
• Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
• Bridging the Gap between User Intent and LLM: A Requirement Alignment Approach for Code Generation
• CHESS: Contextual Harnessing for Efficient SQL Synthesis
• Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
• LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• Hallucination Detection for LLM-based Text-to-SQL Generation via Two-Stage Metamorphic Testing
• Structure Guided Large Language Model for SQL Generation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems