Skip to main content
Search

# Text-to-SQL

4 related articles

Subscribe to updates
  1. arXiv

    Verified SQL history need not be rebuilt each time: MEM-SQL lifts execution accuracy from 37.1% to 50.0% on HARE while cutting input tokens by 76.6%

    When users query the same database repeatedly, previously verified SQL often already contains the joins or computations a new question needs, yet standard benchmarks score each question in isolation and never see that reusable history. MEM-SQL stores history in three layers, whole-query templates, reusable SQL blocks and schema concepts, and admits a layer only when every requirement assigned to it clears that layer's threshold, consulting the database schema only when no layer qualifies or the generator judges the evidence insufficient. Across six language models on the 1,600 HARE requests, mean execution accuracy rises from 37.1% for direct generation without history to 50.0%, with 76.6% fewer input tokens and 68.8% lower latency on average.

  2. NVIDIA open-sources Auto Ontology: an enterprise context layer that aligns metric definitions before an agent answers

    NVIDIA released Auto Ontology, an open library that builds a context layer from enterprise metadata and tells AI agents where data lives, what a metric means, whether to use it, how to use it, where it came from, and what is similar. It generates enterprise ontologies from metadata, connects existing ontologies and semantic models, and reconciles conflicting definitions across systems. It then exposes that context to any agent harness through MCP, CLI, and API, returning provenance with every answer. The library is distributed under Apache License 2.0 and is not currently accepting external contributions.

  3. arXiv

    Opaque integer keys push general Text-to-SQL below 50% on financial data; FLINT adds a lookup agent to close the gap

    FLINT, a Text-to-SQL system for production financial databases, grounds natural-language questions in question-specific table constraints instead of relying on column-name similarity. General systems do well on benchmarks like Spider and BIRD, where schemas are shallow and column values are readable, but financial databases store concepts as opaque integer keys, so even simple queries need multiple joins and those methods fall below 50%. FLINT resolves concepts with a lookup agent, retrieves structurally similar query templates, and prunes large schemas along foreign-key chains; on two datasets totaling 359 questions over production financial schemas it outperforms baselines using the same LLM, and it is deployed in a financial data retrieval service.

  4. arXiv

    PlanPool externalizes clarification as a mutable question pool, improving ambiguity coverage and cutting silent failures across three benchmarks

    The work argues that in agentic Text-to-SQL a correct execution result does not necessarily mean the underlying underspecification has been adequately resolved, since the agent may silently make unverified assumptions that happen to match the intended answer; it attributes this partly to premature clarification termination and introduces PlanPool, which externalizes the clarification plan as a mutable question pool where every planned question must be explicitly asked or dropped before submission and newly discovered ambiguities can be added during interaction, consistently improving ambiguity coverage and reducing silent failures across three benchmarks derived from BIRD-Interact and Spider while maintaining competitive execution accuracy.

You’re all caught up