Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

• URL: http://arxiv.org/abs/2603.07449v1
• Date: Sun, 08 Mar 2026 03:56:15 GMT
• Title: Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System
• Abstract summary: We present Dial, a knowledge-grounded framework for dialect-specific NL2.<n>Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines.
• Score: 25.3445257884901
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference. In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into (i) a canonical syntax reference, (ii) a declarative function repository, and (iii) a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines. The code is at https://github.com/weAIDB/Dial.

Related papers

• 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)
• CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems [13.595364881493943]
  Existing benchmarks typically assume a single source of ambiguity and rely on user interaction for resolution.<n>We introduce Clarity, a framework for automatically generating an NL2 benchmark with multi-faceted ambiguities and diverse user behaviors.<n>Our results highlight the need for more robust ambiguity detection and resolution in industry-grade NL2 systems.
  arXiv  Detail & Related papers  (2026-04-24T07:47:16Z)
• IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages [5.678442494739663]
  IndicDB is a benchmark for evaluating cross-lingual semantic parsing across diverse Indic languages.<n> relational schemas are sourced from open-data platforms, includingNDAP and the India Data Portal.<n>IndicDB comprises 20 databases across 237 tables, generating 15,617 tasks across English, Hindi, and five Indic languages.
  arXiv  Detail & Related papers  (2026-04-15T10:07:37Z)
• 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)
• Datrics Text2SQL: A Framework for Natural Language to SQL Query Generation [0.0]
  This paper introduces a Retrieval-Augmented Generation (RAG)-based framework designed to generate accuratesql queries by leveraging structured documentation, example-based learning, and domain-specific rules.<n>The paper details the architecture, training methodology, and retrieval logic, highlighting how the system bridges the gap between user intent and database structure without requiringsql expertise.
  arXiv  Detail & Related papers  (2025-04-03T21:09:59Z)
• Valid Text-to-SQL Generation with Unification-based DeepStochLog [13.798222228959132]
  We propose a neurosymbolic framework that imposes syntax and schema constraints with unification-based definite clause grammars.<n>Our framework also builds a bi-directional interface to language models to leverage their natural language understanding abilities.<n>This work is the first step towards extending language models with unification-based grammars.
  arXiv  Detail & Related papers  (2025-03-17T16:21:10Z)
• Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing [56.82807063333088]
  We propose a modular approach that resolves ambiguity using natural language interpretations before mapping these to logical forms.<n>Our approach improves interpretation coverage and generalizes across datasets with different annotation styles, database structures, and ambiguity types.
  arXiv  Detail & Related papers  (2025-02-25T18:42:26Z)
• SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging [30.306023265985658]
  We introduce a framework for generating high-quality synthetic training data for any dialect. We propose a novel Mixture-of-Experts (MoE) that leverages the shared knowledge across dialects.
  arXiv  Detail & Related papers  (2024-08-22T20:50:48Z)
• Improved NL2SQL based on Multi-layer Expert Network [5.921227229250013]
  This study introduces a new approach called Multi-Layer Expert Generate SQL (MLEG-), which utilizes a dedicated multi-task hierarchical network. The lower layer of the network extracts semantic features of natural language statements, while the upper layer builds a specialized expert system for specific classification tasks. This hierarchical approach mitigates performance degradation resulting from different task conflicts.
  arXiv  Detail & Related papers  (2023-06-30T15:16:52Z)
• Wav2SQL: Direct Generalizable Speech-To-SQL Parsing [55.10009651476589]
  Speech-to-Spider (S2Spider) aims to convert spoken questions intosql queries given databases. We propose the first direct speech-to-speaker parsing model Wav2 which avoids error compounding across cascaded systems. Experimental results demonstrate that Wav2 avoids error compounding and achieves state-of-the-art results by up to 2.5% accuracy improvement over the baseline.
  arXiv  Detail & Related papers  (2023-05-21T19:26:46Z)
• Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database [86.03294330305097]
  We propose a unified semantic element for question answering (QA) on both knowledge bases (KB) and databases (DB) We introduce the primitive (relation and entity in KB, table name, column name and cell value in DB) as an essential element in our framework. We leverage the generator to predict final logical forms by altering and composing topranked primitives with different operations.
  arXiv  Detail & Related papers  (2022-11-09T19:33:27Z)
• xDBTagger: Explainable Natural Language Interface to Databases Using Keyword Mappings and Schema Graph [0.17188280334580192]
  Translating natural language queries into structured query language (NLQ) in interfaces to relational databases is a challenging task. We propose xDBTagger, an explainable hybrid translation pipeline that explains the decisions made along the way to the user both textually and visually. xDBTagger is effective in terms of accuracy and translates the queries more efficiently compared to other state-of-the-art pipeline-based systems up to 10000 times.
  arXiv  Detail & Related papers  (2022-10-07T18:17:09Z)
• Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding [84.04706075621013]
  We present a general-purpose, modular neural semantic parsing framework based on token-level fine-grained query understanding. Our framework consists of three modules: named entity recognizer (NER), neural entity linker (NEL) and neural entity linker (NSP)
  arXiv  Detail & Related papers  (2022-09-28T21:00:30Z)
• Photon: A Robust Cross-Domain Text-to-SQL System [189.1405317853752]
  We present Photon, a robust, modular, cross-domain NLIDB that can flag natural language input to which a mapping cannot be immediately determined. The proposed method effectively improves the robustness of text-to-native system against untranslatable user input.
  arXiv  Detail & Related papers  (2020-07-30T07:44:48Z)

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.