Pith. sign in

REVIEW 8 cited by

The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.07702 v2 pith:IHOBR7AC submitted 2024-08-14 cs.CL

Karime Maamari , Fadhil Abubaker , Daniel Jaroslawicz , Amine Mhedhbi This is my paper
classification cs.CL
keywords schemalinkingtext-to-sqlgenerationmodelsaccuracycolumnselements
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's query while disregarding irrelevant ones. However, imperfect schema linking can often exclude required columns needed for accurate query generation. In this work, we revisit schema linking when using the latest generation of large language models (LLMs). We find empirically that newer models are adept at utilizing relevant schema elements during generation even in the presence of large numbers of irrelevant ones. As such, our Text-to-SQL pipeline entirely forgoes schema linking in cases where the schema fits within the model's context window in order to minimize issues due to filtering required schema elements. Furthermore, instead of filtering contextual information, we highlight techniques such as augmentation, selection, and correction, and adopt them to improve the accuracy of our Text-to-SQL pipeline. Our approach ranks first on the BIRD benchmark achieving an accuracy of 71.83%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL

    cs.CL 2025-07 conditional novelty 6.0 of 10

    RASL retrieves relevant tables and columns for text-to-SQL by decomposing schemas into semantic entities, calibrating entity-type importance on training data, and using an LLM to rank candidates, beating baselines on ...

  2. Text-to-SQL for Enterprise Data Analytics

    cs.CL 2025-07 conditional novelty 6.0 of 10

    An enterprise Text-to-SQL chatbot augmented with a knowledge graph, context ranking, and query-fixing agents achieves 53% correct or nearly correct answers on LinkedIn's internal benchmark, with knowledge graph compon...

  3. How Many Instructions Can LLMs Follow at Once?

    cs.AI 2025-07 conditional novelty 6.0 of 10

    IFScale measures instruction-following at densities from 10 to 500 constraints and finds that even top frontier models satisfy only about two-thirds of 500 simultaneous keyword instructions.

  4. SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SEED automatically generates evidence from database schemas, descriptions, and sampled values, improving text-to-SQL accuracy in no-evidence settings.

  5. SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SQLens uses weak supervision over database and LLM error signals to detect clause-level semantic errors in text-to-SQL and fixes them iteratively, improving execution accuracy on BIRD and Spider.

  6. Automatic Metadata Extraction for Text-to-SQL

    cs.DB 2025-05 conditional novelty 6.0 of 10

    LLM-generated summaries of database profiling statistics outperform human-written metadata for text-to-SQL on BIRD, and a SQL-generation-based schema linker adds further gains.

  7. AttnLink: Turning Attention into Schema Links for Text-to-SQL

    cs.CL 2026-08 conditional novelty 5.0 of 10

    Attention from an LLM's generation-start position, pooled over schema candidates, yields millisecond-scale, controllable schema-linking scores that beat prior linkers on three benchmarks.

  8. Effectiveness of Prompt Optimization in NL2SQL Systems

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Iterative prompt optimization with an LLM proposer improves NL2SQL accuracy and prompt compactness on BIRD dev, and a latency-aware variant reduces worst-case SQL execution time.

Pith tools