构建首个印度语多语言文本转SQL基准，评估跨语言语义解析能力。
IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages
- 用三智能体框架构建20个真实政府数据库的复杂关系结构
- 生成15617个任务，英印语言间性能差9.00%，暴露'印语差距'
- 适合关注非西方语言、真实数据场景的AI研究者
尽管大语言模型显著提升了文本转SQL的性能，现有基准仍主要聚焦西方语境和简化模式，难以覆盖真实世界的非西方应用。本文提出IndicDB，一个面向印度语族多语言文本转SQL的基准，用于评估跨语言语义解析能力。其关系模式源自开放数据平台（如国家数据与分析平台NDAP、印度数据门户IDP），确保行政数据的真实复杂性。IndicDB包含20个数据库，共237张表。通过迭代式三智能体框架（架构师、审计员、优化者）将非规范化政府数据转化为高密度关系结构（平均每库11.85张表，连接深度达六层）。该流程具备值感知、难度校准与连接强制特性，生成涵盖英语、印地语及五种印地语族语言的15,617个任务。我们评估了DeepSeek v3.2、MiniMax 2.7、LLaMA 3.3、Qwen3等前沿模型在七种语言变体上的表现。结果显示，从英语到印地语族语言性能下降9.00%，揭示‘印地语差距’，主因包括更难的模式关联、更高结构歧义以及外部知识匮乏。IndicDB为多语言文本转SQL提供严谨评测标准。代码与数据：https://anonymous.4open.science/r/multilingualText2Sql-Indic--DDCC/
原文摘要 · Abstract (English)
While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks predominantly focus on Western contexts and simplified schemas, leaving a gap in real-world, non-Western applications. We present IndicDB, a multilingual Text-to-SQL benchmark for evaluating cross-lingual semantic parsing across diverse Indic languages. The relational schemas are sourced from open-data platforms, including the National Data and Analytics Platform (NDAP) and the India Data Portal (IDP), ensuring realistic administrative data complexity. IndicDB comprises 20 databases across 237 tables. To convert denormalized government data into rich relational structures, we employ an iterative three-agent framework (Architect, Auditor, Refiner) to ensure structural rigor and high relational density (11.85 tables per database; join depths up to six). Our pipeline is value-aware, difficulty-calibrated, and join-enforced, generating 15,617 tasks across English, Hindi, and five Indic languages. We evaluate cross-lingual semantic parsing performance of state-of-the-art models (DeepSeek v3.2, MiniMax 2.7, LLaMA 3.3, Qwen3) across seven linguistic variants. Results show a 9.00% performance drop from English to Indic languages, revealing an "Indic Gap" driven by harder schema linking, increased structural ambiguity, and limited external knowledge. IndicDB serves as a rigorous benchmark for multilingual Text-to-SQL. Code and data: https://anonymous.4open.science/r/multilingualText2Sql-Indic--DDCC/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。