# Bootstrapping Semantic Layer from Execution for Text-to-SQL

arXiv: https://arxiv.org/abs/2606.05634 · HTML: https://mlsanity.com/paper/2606.05634/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 13 of 13)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM](https://mlsanity.com/paper/2402.11517/) (2024)
- [Automatic Metadata Extraction for Text-to-SQL](https://mlsanity.com/paper/2505.19988/) (2025)
- [Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge](https://mlsanity.com/paper/2301.01067/) (2023)
- [Semantic Decomposition of Question and SQL for Text-to-SQL Parsing](https://mlsanity.com/paper/2310.13575/) (2023)
- [Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL](https://mlsanity.com/paper/2310.18742/) (2023)
- [You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL](https://mlsanity.com/paper/2409.12172/) (2024)
- [Knowledge Base Construction for Knowledge-Augmented Text-to-SQL](https://mlsanity.com/paper/2505.22096/) (2025)
- [Query and Conquer: Execution-Guided SQL Generation](https://mlsanity.com/paper/2503.24364/) (2025)
- [AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views](https://mlsanity.com/paper/2604.07041/) (2026)

## Abstract (arXiv)

Real-world text-to-SQL is often under-specified until user phrases are grounded in how the database stores values. Prior work attempts to address this by requiring a semantic layer to specify groundings in advance, but such specifications are often incomplete, especially in expert domains where domain-specific conventions are under-documented. As this leaves multiple grounding hypotheses open for the same SQL part, we introduce GATE (Grouding After Test from Execution), which bootstraps missing groundings from execution feedback. GATE keeps grounding hypotheses open while executing the already grounded parts to obtain observations. Then, only the hypothesis supported by that observation is grounded and stored as a memory entry, recording what was tested and how the open part should be written in SQL. These entries accumulate into execution-grounded memory, allowing later steps to reuse supported groundings. Across real-world and controlled benchmarks, GATE consistently improves over strong baselines, demonstrating that execution can serve not only as validation but also as a bootstrapping mechanism for reusable memory in text-to-SQL.