← Back to all news
arXiv Computation and Language By Keti Korini, Christian Bizer

SINT-Flow: Schema Integration using Large Language Model Workflows

Read the original on arXiv Computation and Language →

SINT-Flow is a schema integration framework that uses five large language model (LLM) operators to automatically produce a unified schema from multiple input tables, even when those tables are denormalized and contain attributes for several entity types. The framework decomposes such tables into entity‑specific relations during integration. Evaluation on the newly introduced SINT‑Bench benchmark, using GPT‑5.2 and Qwen‑3.6‑27B, shows high performance with at least 97% completeness in entity type detection, 81% attribute detection, and an 84% F1‑score for schema mapping, while ablation studies confirm the benefits of self‑consistency and a review loop.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Aug 7

Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data

arXiv:2608. 06331v1 Announce Type: cross Abstract: From natural-language query interfaces to automated report generation, data analysis tools need a description of the data: the real-world entities it contains, which columns function as measures or identifiers, and how tables connect into units of analysis.

By Donna Hooshmand, Shubham Shahi, Cameron Barrie, Abhratanu Dutta, Marko Sterbentz, Harper Pack, Kristian J. Hammond
llmsbenchmarks
More like this →
arXiv AI
Sep 17

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

The paper examines the role of schema linking in Text-to-SQL systems and finds that recent large language models can effectively use relevant schema elements even when many irrelevant ones are present. Consequently, the authors eliminate schema linking when the entire schema fits within the model’s context window, instead employing augmentation, selection, and correction techniques to enhance accuracy. Their approach achieves first place on the BIRD benchmark with a 71.83% accuracy.

By Karime Maamari, Fadhil Abubaker, Daniel Jaroslawicz, Amine Mhedhbi
llmsbenchmarksdata-engineering
More like this →
arXiv Machine Learning
Jul 27

SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text

arXiv:2607. 21610v1 Announce Type: cross Abstract: Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available.

By Miaobo Hu, Xiaobo Guo, Shuhao Hu, Bokun Wang, Rui Chen, Xin Wang, Daren Zha, Jun Xiao
llmsreinforcement-learningbenchmarks
More like this →
arXiv AI
Oct 9

An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment

The paper introduces an explainable, header‑centric framework for semantic table interpretation and data quality assessment that operates solely on column headers. It maps headers to 39 interpretable types using curated lexical resources, applies validation rules to detect data quality issues, and aggregates these into a lightweight quality metric called HeadersIQ. The framework was evaluated on diverse benchmarks, demonstrating broad coverage of noisy real‑world metadata and providing a workflow for metadata‑driven semantic annotation, quality monitoring, and benchmark diagnosis.

By Marcelo Valentim Silva, Hannes Herrmann, Valerie Maxville
benchmarkssafetydata-engineering
More like this →