The paper presents a multi‑agent, persona‑driven NL2SQL framework that addresses common LLM shortcomings such as schema hallucination, syntax errors, and intent mismatch. It incorporates domain relevance detection, schema‑grounded knowledge construction, KPI‑aware SQL synthesis, syntax‑level self‑repair via sqlite feedback, and semantic consistency checking through SQL‑to‑NL reverse engineering. Evaluated on 60 queries, the system achieves 90% correctness using Mistral across seven coordinated LLM calls, demonstrating a significant improvement in reliability for high‑stakes environments.
By Anjali Vemula, Akshat Dasula
IndicDBBench is a new multilingual Text-to-SQL benchmark that evaluates cross‑lingual semantic parsing across 20 databases and 237 tables in seven languages, including English and six Indic languages. The benchmark uses real‑world open‑data schemas from NDAP and IDP, and a three‑agent pipeline to create complex relational structures with high relational density and join depths up to six. Evaluation of state‑of‑the‑art models shows a 9‑point drop in execution accuracy from English to Indic languages, revealing an "Indic Gap" that persists even when gold tables and literal values are supplied.
By Aviral Dawar, Roshan Karanth, Vikram Goyal, Rakhee Kulshrestha, Sumanta Pasari, Dhruv Kumar
arXiv:2607. 06229v1 Announce Type: cross Abstract: Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extraction, similarity search, and aggregation within ordinary SQL queries.
By Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He
The paper presents a framework for translating natural‑language queries into Kusto Query Language (KQL) using small language models (SLMs). It introduces lightweight retrieval, error‑aware prompting, LoRA fine‑tuning with rationale distillation, and a two‑stage architecture that pairs an SLM drafter with a low‑cost LLM judge. Evaluations on Microsoft’s NL2KQL Defender dataset show the two‑stage approach achieving high syntax and schema‑valid accuracy while dramatically reducing cost compared to larger LLM baselines.
By Saleha Muzammil, Rahul Reddy, Vishal Kamalakrishnan, Hadi Ahmadi, Wajih Ul Hassan
arXiv:2608. 16663v1 Announce Type: cross Abstract: Direct text-to-SQL asks a language model to do two jobs: interpret the business question and construct the complete relational query.
By Yi Ai
arXiv:2606. 08018v1 Announce Type: new Abstract: Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects.
By Jianling Gao, Chongyang Tao, Jiayuan Bai, Liu Yang, Xuanguang Pan, Jinrui Liu, Shihao Xing, Xiaohan Xu, Jie Liang, Shuai Ma
Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queries, policy failures, cost, and nondeterminism. SemPlan Benchmark evaluates this architectural design space with a deterministic synthetic bilingual benchmark containing 1,800 cases in English and Brazilian Portuguese; 1,200 cases form the frozen scientific evaluation subset.
arXiv:2609.08950v1 Announce Type: cross
Abstract: Text-to-SQL systems translate natural language queries into executable SQL, democratizing access to structured data. Despite recent advances driven b...
By Mohammadhossein Malekpour, Mohamed Riahi, Maxime Lamothe, Amine Mhedhbi
arXiv:2608. 13612v1 Announce Type: new Abstract: Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queries, policy failures, cost, and nondeterminism.
By Bruno Santos Teixeira
arXiv:2606. 02109v1 Announce Type: new Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approaches fundamentally different from academic benchmarks.
By Shannon Serrao, Soumitra Chatterjee, Dorina Strori, Abhishek Sharma, Nathan Miller
arXiv:2602. 16720v2 Announce Type: replace-cross Abstract: Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments.
By Bowen Cao, Weibin Liao, Yushi Sun, Dong Fang, Haitao Li, Wai Lam
text2ql is an open‑source Python framework that enables natural language querying of databases without relying on large language models at query time. It uses a language‑agnostic intermediate representation (QueryIR) and a pluggable renderer to support both SQL and GraphQL targets through a single seven‑stage detection pipeline. In deterministic mode, it achieves 100% execution accuracy with a median latency of 3.2 ms, while the LLM‑backed mode delivers 62‑70% exact match and 84‑91% execution accuracy on benchmark samples.
By Ritesh Kumar