Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding

• URL: http://arxiv.org/abs/2604.28028v1
• Date: Thu, 30 Apr 2026 15:44:34 GMT
• Title: Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding
• Abstract summary: Large language models (LLMs) have revolutionized Text-to-generation, allowing users to query structured data using natural language with growing ease.<n>We introduce TeCoD, a system that harnesses the recurrence of query patterns in labeled workloads.<n>We show how TeCoD can yield up to 36% higher execution accuracy than in-context learning (ICL) and 2.2x lower latency on matched queries.
• Score: 19.55574267306257
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing ease. Yet, real-world deployment remains challenging, especially in complex or unseen schemas, due to inconsistent accuracy and the risk of generating invalid SQL. We introduce Template Constrained Decoding (TeCoD), a system that addresses these limitations by harnessing the recurrence of query patterns in labeled workloads. TeCoD converts historical NL-SQL pairs into reusable templates and introduces a robust template selection module that uses a fine-tuned natural language inference model to match or reject queries efficiently. Once the template is selected, TeCoD enforces it during SQL generation through grammar-constrained decoding, implemented via a novel partitioned strategy that ensures both syntactic validity and efficiency. Together, these components yield up to 36% higher execution accuracy than in-context learning (ICL) and 2.2x lower latency on matched queries.

Related papers

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows [54.49251107006261]
  We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform.<n>We find that the strongest proprietary models reach 67-70% execution accuracy while the best open-source model achieves 58.1%.
  arXiv  Detail & Related papers  (2026-07-07T12:54:08Z)
• ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement [57.98138819417949]
  We propose ErrorLLM, a framework that explicitly models text-to- querying.<n>We show that ErrorLLM achieves the most significant improvements over backbone initial generation.<n>ErrorLLM addresses both sides by high detection F1 score while maintaining refinement effectiveness.
  arXiv  Detail & Related papers  (2026-03-04T05:27:20Z)
• RingSQL: Generating Synthetic Data with Schema-Independent Templates for Text-to-SQL Reasoning Models [1.0062127381149395]
  Ring is a hybrid data generation framework that combines schema-independent query templates with LLM-based paraphrasing of natural language questions.<n>We find that models trained by Ring achieve an average gain in accuracy of +2.3% across six text-to- benchmarks when compared to models trained on other synthetic data.
  arXiv  Detail & Related papers  (2026-01-09T00:46:53Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction [5.123751486259634]
  We introduce LitE-, a Lightweight and Efficient framework with two components.<n>On BIRD, LitE- achieves 72.10% execution accuracy, and on Spider it reaches 88.45%, demonstrating comparable or superior performance to Retriever.<n>Our findings demonstrate that high-quality Text-to-correction generation is feasible with lightweight models, offering a practical solution for privacy-sensitive and resource-constrained settings.
  arXiv  Detail & Related papers  (2025-10-10T05:27:47Z)
• RetrySQL: text-to-SQL training with retry data for self-correcting query generation [1.6707278580444538]
  We introduce Retry, a new approach to training text-to-generation models.<n>We demonstrate that retry steps yield an improvement of up to 4 percentage points in both overall and challenging execution accuracy metrics.
  arXiv  Detail & Related papers  (2025-07-03T11:00:49Z)
• Rationalization Models for Text-to-SQL [13.792561265515003]
  We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-thought model fine-tuning.<n>The process begins with manually annotating a small set of examples, which are then used to prompt a large language model.<n>A rationalization model is subsequently trained on the validated queries, enabling extensive synthetic CoT annotations.
  arXiv  Detail & Related papers  (2025-02-10T18:38:57Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring [11.78795632771211]
  We introduce a novel benchmark designed to evaluate text-to- reliability as a model's ability to correctly handle any type of input question. We evaluate existing methods using a novel penalty-based scoring metric with two modeling approaches.
  arXiv  Detail & Related papers  (2024-03-23T16:12:52Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)
• Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing [66.55478402233399]
  We propose a framework to elicit relational structures via a probing procedure based on Poincar'e distance metric. Compared with commonly-used rule-based methods for schema linking, we found that probing relations can robustly capture semantic correspondences. Our framework sets new state-of-the-art performance on three benchmarks.
  arXiv  Detail & Related papers  (2022-06-28T14:05:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.