T5QL: Taming language models for SQL generation

• URL: http://arxiv.org/abs/2209.10254v1
• Date: Wed, 21 Sep 2022 10:43:13 GMT
• Title: T5QL: Taming language models for SQL generation
• Abstract summary: Current SOTA methods for semantic parsing depend on LLMs to achieve high predictive accuracy on benchmark datasets. We propose T5QL, a new method that improves the performance in benchmark datasets when using smaller LMs, namely T5-Base, by 13pp when compared against SOTA methods.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Automatic SQL generation has been an active research area, aiming at streamlining the access to databases by writing natural language with the given intent instead of writing SQL. Current SOTA methods for semantic parsing depend on LLMs to achieve high predictive accuracy on benchmark datasets. This reduces their applicability, since LLMs requires expensive GPUs. Furthermore, SOTA methods are ungrounded and thus not guaranteed to always generate valid SQL. Here we propose T5QL, a new SQL generation method that improves the performance in benchmark datasets when using smaller LMs, namely T5-Base, by 13pp when compared against SOTA methods. Additionally, T5QL is guaranteed to always output valid SQL using a context-free grammar to constrain SQL generation. Finally, we show that dividing semantic parsing in two tasks, candidate SQLs generation and candidate re-ranking, is a promising research avenue that can reduce the need for large LMs.

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)
• CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking process [1.4328341467798655]
  We propose a novel framework for efficiently fine-tuning SLMs on Text-to-SOTA tasks.<n>Its main innovation lies in the Linking phase, where a search combined with model internal confidence is employed.<n>Our method achieves state-of-the-art results on Text-to-SOTA tasks via SLMs.
  arXiv  Detail & Related papers  (2026-06-17T08:51:43Z)
• UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL [27.963417399820987]
  We introduce UniQL, a human-verified benchmark for cross-dialect text-to- evaluation.<n>All dialects share the same intents, aligned schemas and database contents, enabling controlled evaluation of dialect generalization.
  arXiv  Detail & Related papers  (2026-06-06T07:14:53Z)
• FINER-SQL: Boosting Small Language Models for Text-to-SQL [40.19592881059662]
  Large language models suffer from high computational cost, long latency, and data privacy concerns.<n>A natural alternative is to use small language models, which enable efficient and private on-premise deployment.<n>We propose FINER-sql, a scalable and reusable reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-05-05T07:51:29Z)
• PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation [21.0303026118673]
  We introduce PARROT, a practical and realistic benchmak for CrOss-System SQL Translation.<n> PARROT comprises 598 translation pairs from 38 open-source benchmarks and real-world business services.<n>We also provide multiple benchmark variants, including PARROT-Diverse with 28,003 translations and PARROT-Simple with 5,306 representative samples.
  arXiv  Detail & Related papers  (2025-09-27T14:41:13Z)
• End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation [6.5390580456423555]
  Traditional approaches model text-to- query as a direct translation task.<n>Recent advances in large language models (LLMs) have significantly improved translation accuracy.<n>We propose a three-stage end-to-end text-to-end framework to identify the user's intended database.
  arXiv  Detail & Related papers  (2025-08-08T15:16:36Z)
• SLM-SQL: An Exploration of Small Language Models for Text-to-SQL [0.0]
  Small language models (SLMs) offer inherent advantages in inference speed and suitability for edge deployment.<n>We leverage recent advancements in post-training techniques to explore Textto- applications.<n> Experimental results validate the effectiveness and generalizability of our method.
  arXiv  Detail & Related papers  (2025-07-30T08:29:07Z)
• Weaver: Interweaving SQL and LLM for Table Reasoning [62.55797244714265]
  Weaver generates a flexible, step-by-step plan that combinessql for structured data retrieval with LLMs for semantic processing.<n>Weaver consistently outperforms state-of-the-art methods across four TableQA datasets.
  arXiv  Detail & Related papers  (2025-05-25T03:27:37Z)
• ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects [24.450818792474216]
  This work introduces Exe, a text-to-guided framework with execution-driven, agentic bootstrapping.<n>We show that Exe bridges the dialect gap in text-to-guided learning, achieving average improvements of 15.2%, 10.38%, and 4.49% over GPT-4o on, and Oracle, respectively.
  arXiv  Detail & Related papers  (2025-05-22T19:13:34Z)
• SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL [11.713258980098296]
  We propose a Self-Reward-based search method designed to enhance the reasoning ability of large language models (LLMs) Our code is publicly available at:https://github.com/ShuaiLyu01T-o1.
  arXiv  Detail & Related papers  (2025-02-17T12:28:11Z)
• 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)
• Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement [1.392448435105643]
  Text-to-s enables non-expert users to effortlessly retrieve desired information from databases using natural language queries. Current state-of-the-art (SOTA) models like GPT4 and T5 have shown impressive performance on large-scale benchmarks like BIRD. This paper proposed a novel approach that only needs SQL Quality to enhance Text-to-s performance.
  arXiv  Detail & Related papers  (2024-10-02T17:21:51Z)
• Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation [10.812409371488913]
  We propose a unified generate-then-rank framework that can be flexibly incorporated with existing NLIDBs to consistently improve translation accuracy. Metasql introduces query metadata to control the generation of better query candidates and uses learning-to-rank algorithms to retrieve globally optimized queries. The results show that the performance of the translation models can be effectively improved using Metasql.
  arXiv  Detail & Related papers  (2024-02-27T02:16:07Z)
• Fine-Tuning Language Models for Context-Specific SQL Query Generation [0.0]
  This paper presents a novel approach to fine-tuning open-source large language models (LLMs) for the task of transforming natural language intosql queries. We introduce models specialized in generatingsql queries, trained on synthetic datasets tailored to the Snowflake SQL and Google dialects. Our methodology involves generating a context-specific dataset using GPT-4, then fine-tuning three open-source LLMs(Starcoder Plus, Code-Llama, and Mistral) employing the LoRa technique to optimize for resource constraints. The fine-tuned models demonstrate superior performance in zero-shot settings compared to the baseline GP
  arXiv  Detail & Related papers  (2023-12-04T18:04:27Z)
• Benchmarking and Improving Text-to-SQL Generation under Ambiguity [25.283118418288293]
  We develop a novel benchmark called AmbiQT where each text is interpretable as two plausible SQLs due to lexical and/or structural ambiguity. We propose LogicalBeam, a new decoding algorithm that navigates thesql logic space using a blend of plan-based template generation and constrained infilling.
  arXiv  Detail & Related papers  (2023-10-20T17:00:53Z)
• 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)
• Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing [56.232873134174056]
  One of the major challenges in text-to-text parsing is domain generalization, i.e., how to well generalize to unseen databases. In this work, we explore ways to further augment the pre-trained text-to-text transformer model with specialized components for text-to-text parsing. To this end, we propose a new architecture GRAPHIX-T5, augmented by some specially-designed graph-aware model with layers.
  arXiv  Detail & Related papers  (2023-01-18T13:29:05Z)
• A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions [102.8606542189429]
  The goal of text-to-corpora parsing is to convert a natural language (NL) question to its corresponding structured query language () based on the evidences provided by databases. Deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output query.
  arXiv  Detail & Related papers  (2022-08-29T14:24:13Z)
• Weakly Supervised Text-to-SQL Parsing through Question Decomposition [53.22128541030441]
  We take advantage of the recently proposed question meaning representation called QDMR. Given questions, their QDMR structures (annotated by non-experts or automatically predicted) and the answers, we are able to automatically synthesizesql queries. Our results show that the weakly supervised models perform competitively with those trained on NL- benchmark data.
  arXiv  Detail & Related papers  (2021-12-12T20:02:42Z)
• SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Language [5.0873556718569155]
  General purpose natural language that interfaces to information stored within databases requires flexibly translating natural language questions into database queries. The best performing text-to-generator systems approach this task by first converting questions into an intermediate logical form (LF) (Lyu et al. ( 2020)) We approach direct conversion of questions tosql statements using T5 (Raffel et al.), a pre-text generation model, modified to support pointer-style decoding (See et al.) The performance improvement is 6.6% absolute over the prior state-of-the-art (Min et al.) and approaches the performance of state
  arXiv  Detail & Related papers  (2020-11-07T19:22:59Z)
• Structure-Grounded Pretraining for Text-to-SQL [75.19554243393814]
  We present a novel weakly supervised StructureStrued pretraining framework (G) for text-to-LARGE. We identify a set of novel prediction tasks: column grounding, value grounding and column-value mapping, and leverage them to pretrain a text-table encoder.
  arXiv  Detail & Related papers  (2020-10-24T04:35:35Z)

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.