Schema Linking

Follow this topic Ask about this topic

Schema linking studies how to find the database tables, columns, and relationships that correspond to a natural-language question, enabling systems to generate grounded SQL or knowledge-graph queries. Common approaches use embedding-based retrieval, language-model reasoning, attention scores, and multi-stage or hierarchical search; some systems also inspect schemas or data interactively and use execution feedback to refine links. The task matters especially for large, unfamiliar, or changing databases, where schemas may be opaque, distributed, or too large to provide in full. A central challenge is balancing coverage of all relevant schema elements against irrelevant links, computational cost, and downstream query accuracy, with standalone retrieval evaluation complementing end-to-end text-to-SQL benchmarks.

Latest papers

15 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data
Oct 2, 2026Arijit Sehanobish, Bruno Gomes Coelho, Guillaume Michel +3Text-to-SQL Financial QA
Kensho Technologies
Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case
Aug 27, 2026Ahlame Diouan, Eric Ferey, Sabine Loudcher +1Schema Linking Tabular Representation Learning
ERIC, UL2 · Université Lumière Lyon 2, UR ERIC, Lyon, France · Bial-X, Lyon, France
AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs
Aug 14, 2026Yiming Zhang, Koji TsudaNatural Language to SPARQL Schema Linking
The University of Tokyo Kashiwa, Chiba, Japan · Center for Basic Research on Materials, National Institute for Materials Science Tsukuba, Ibaraki, Japan · RIKEN Center for Advanced Intelligence Project Tokyo, Japan
DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
Aug 12, 2026Anik Pramanik, Murat Kantarcioglu, Vincent Oria +1LLM Prompting Schema Linking
New Jersey Institute of Technology, USA. · Virginia Tech, USA.
MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL
Aug 10, 2026Beiyu Xu, Zhenyu Wu, Jiaoyan Chen +1Schema Linking Text-to-SQL
University of Manchester Faculty of Science and Engineering Department of Computer Science
AttnLink: Turning Attention into Schema Links for Text-to-SQL
Aug 1, 2026Jinwang Song, Tao Liu, Haowen Zheng +3Schema Linking Text-to-SQL
SAFAARI: Schema-Aware Framework for Accelerated Advertiser Response Intelligence
Jul 27, 2026Bhanu Teja Rangaraju, Chandan KumarMulti-Agent LLM Systems Customer Support Automation
Amazon, Seattle, USA.
Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval
Jul 14, 2026Qingcheng Zeng, Puxuan Yu, Aman Mehta +2Schema Linking Text-to-SQL
Northwestern University · Snowflake Inc.
How far do on-premises open LLMs get on Text-to-SQL? A cross-family size and technique frontier on BIRD
Jun 29, 2026Vladimir BeskorovainyiLLM Self-Correction LLM Evaluation
Besk Tech | Moscow Institute of Physics and Technology (MIPT)
DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL
Jun 16, 2026Esteban Schafir, Xu Zheng, Hojat Allah Salehi +4Schema Linking Question Decomposition
Florida International University · NEC-Labs · Singapore Management University
ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL
Jun 4, 2026Xiaobing Chen, Ai Jian, Eryu Guo +1Execution-Guided Code Generation Schema Linking
Harbin Engineering University, Harbin, China · Harbin Institute of Technology, Harbin, China · Beijing University of Posts and Telecommunications, Beijing, China
EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
May 28, 2026Huawei Zheng, Sen Yang, Zhaorui Yang +11Schema Linking Text-to-SQL
School of Software Technology, Zhejiang University. · State Key Lab of CAD&CG, Zhejiang University. · Tencent TEG. +1
Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL
May 5, 2026Le Zhou, Feng Yao, Fengcai Qiao +3Schema Linking Text-to-SQL
College of Systems Engineering, National University of Defense Technology · College of Advanced Interdisciplinary Studies, National University of Defense Technology · Institute of Automation, Chinese Academy of Sciences +1
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Mar 17, 2026Ai Jian, Xiaoyun Zhang, Eryu Guo +6Schema Linking Group Relative Policy Optimization
Beijing University of Posts and Telecommunications, Beijing, China · State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences +1
Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
Mar 6, 2026Bingfeng Chen, Shaobin Shi, Yongqi Luo +3Text-to-SQL Schema Linking
School of Computer Science, Guangdong University of Technology · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Peng Cheng Laboratory +1

Oct 2, 2026J/K move · Enter open · S save

From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data

Arijit Sehanobish, Bruno Gomes Coelho, Guillaume Michel, Sophia Zhi+2

Kensho Technologies

Text-to-SQL Financial QA Database Systems Relational Databases Schema Linking

Open paper AskPDF arXiv

General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and column values are often human readable. In production financial databases, where concepts are stored as opaque integer keys rather than human-readable strings, these methods fall below 50%, as even simple queries require multiple joins and filter predicates reference opaque IDs. We present Financial LINking Text-to-SQL (FLINT), a domain-specialized Text-to-SQL system that closes this gap through three key components: (1) a lookup agent that dynamically resolves natural-language concepts to question-specific reference table constraints, (2) embedding-based retrieval of structurally similar query templates from a compact, expert-authored bank, and (3) schema linking that prunes a large table schema to the relevant subset by traversing foreign-key chains, rather than relying on name similarity alone. We evaluate on two datasets totaling 359 questions over production financial schemas. FLINT outperforms various state-of-the-art baselines using the same LLM. The system is deployed in production as part of a financial data retrieval service.