ConStruM: A Structure-Guided LLM Framework for Context-Aware Schema Matching
cs.DB
Submitted: 2026-01-28
Updated: 2026-11-04
Code: https://github.com/construm403/construm
Terminology
Sources
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms
- Schema Matching on Graph: Iterative Graph Exploration for Efficient and Explainable Data Integration
- Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
- ReMatch: Retrieval Enhanced Schema Matching with LLMs
- KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs