analiza aiqbench
CORE-T addresses a critical bottleneck in text-to-SQL workflows by improving the accuracy of multi-table retrieval without requiring additional training data or excessive inference overhead. By leveraging LLM-generated metadata and a lightweight compatibility cache, the framework significantly reduces distractor tables while maintaining high execution accuracy across standard benchmarks like Spider and Bird. This advancement directly enhances the scalability and efficiency of end-to-end database query generation systems.
CORE-T: COherent REtrieval of Tables for Text-to-SQL
arXiv:2601.13111v3 Announce Type: replace-cross Abstract: Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end performance. We study an open-book setting where queries must be answered over large, heterogeneous table collections pooled from many sources, without clean scoping signals such as database identifiers. Here, dense retrieval (DR) achieves high recall but returns many distractors, while join-aware alternatives often rely on extra assumptions and/or incur high inference overhead. We propose CORE-T, a scalable, training-free framework that enriches tables with LLM-generated purpose metadata and pre-computes a lightweight table-compatibility cache. At inference time, DR returns top-K candidates; a single LLM call selects a coherent, joinable subset, and a two-step additive adjustment stage restores strongly compatible tables. Across Bird, Spider, MMQA, and Beaver, CORE-T improves over DR by up to 22.7 points in table-selection F1 while returning up to 40% fewer tables, and by up to 24.4 points in multi-table execution accuracy, and uses 1.64-4.20x fewer total selection tokens than LLM-intensive baselines.
Abstract:Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end performance. We study an open-book setting where queries must be answered over large, heterogeneous table collections pooled from many sources, without clean scoping signals such as database identifiers. Here, dense retrieval (DR) achieves high recall but returns many distractors, while join-aware alternatives often rely on extra assumptions and/or incur high inference overhead. We propose CORE-T, a scalable, training-free framework that enriches tables with LLM-generated purpose metadata and pre-computes a lightweight table-compatibility cache. At inference time, DR returns top-K candidates; a single LLM call selects a coherent, joinable subset, and a two-step additive adjustment stage restores strongly compatible tables. Across Bird, Spider, MMQA, and Beaver, CORE-T improves over DR by up to 22.7 points in table-selection F1 while returning up to 40% fewer tables, and by up to 24.4 points in multi-table execution accuracy, and uses 1.64-4.20x fewer total selection tokens than LLM-intensive baselines.
Accepted at EMNLP Main 2026. Camera-ready version with revisions following peer review. Code and data available at: this https URL
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
arXiv:2601.13111 [cs.CL]
(or arXiv:2601.13111v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2601.13111 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 286 cuvinte
Subiecte conexe
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026
How Guardoc transforms medical document processing with Amazon Nova models
AWS · 27 iul. 2026
Introducing Instella-MoE: A State-of-the-Art Fully Open Mixture-of-Experts Language Model
AMD · 24 iul. 2026