Skip to content

DataMosaic: An Interactive Demonstration of Constraint-Driven Document-to-Database Construction

Aug 2026 · Proceedings of the VLDB Endowment · Vol 19, pp. 4570-4573 · 2 citations · 6 references

TL;DR

DataMosaic is presented, an interactive system for constraint-driven document-to-database construction that incrementally builds entity and relationship tables through a closed loop of extraction, verification, repair, and targeted re-extraction.

Abstract

Large language models (LLMs) have improved document information extraction, but turning extracted facts into relational databases remains fundamentally difficult. The challenge is that extraction is local to text, whereas database construction must satisfy global semantics defined by schemas, keys, and integrity constraints. Consequently, single-pass LLM extraction often produces inconsistent tuples, missing links, and semantically invalid results. We present DataMosaic , an interactive system for constraint-driven document-to-database construction. Given raw documents together with user-specified schemas and constraints, DataMosaic incrementally builds entity and relationship tables through a closed loop of extraction, verification, repair, and targeted re-extraction. The system exposes intermediate table snapshots, detected violations, and repair actions, enabling users to audit how database-level feedback improves the final relational output. In the demo, attendees can configure inputs and constraints, inspect real-time analysis logs, and observe how DataMosaic repairs inconsistencies and materializes query-ready relational tables. The demonstration highlights how integrating extraction with verification and repair enables reliable document-to-database construction.

View source

Similar papers

#natural language process... Preprint Oct 2026

Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation

Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attr...

Teng Lin, Xin-Yu Liu, Nan Tang · 1 citation
#artificial intelligence Preprint Sep 2026

BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL

Data agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of columns, so cost constraints may require choosing between table coverage and serialization detail well before the context window is full. We introduce BudgetSchemaBench,...

Chen Shen · 0 citations
Open access Oct 2026

IncrConsist: Efficient Incremental Consistency Maintenance for LLM-Maintained Knowledge Bases

The results demonstrate that incremental affected-set computation—a classical technique in database materialization and ontology maintenance—can be adapted to LLM-maintained text knowledge bases, through extensions for typed provenance strength and lexical mutex conflict.

Bai-Ling Zhang · 0 citations
#natural language process... Preprint Sep 2026

TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA

Finding a relevant paper is not the same as producing a verifiable answer from it. LitTraceQA requires canonical paper identifiers, exact evidence at the page or object level, and typed answers that match the evaluator. We call the separation between source access and scorer-visible correctness the grounding contract g...

Sachin Gupta, Divya Godara · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.