mlsanityData to 14 Oct 2026

RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching

arXiv 2606.07843 ↗First posted 5 Jun 2026cs.DB cs.IR cs.LGcited by 1

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Schema matching, a critical task for integrating data from diverse sources, seeks to identify correspondences between columns across different schemas. In multi-table holistic schema matching, columns with similar semantic meaning may reside in tables with different contexts due to heterogeneous schema designs, where similarity-based techniques are inadequate. The focus of this paper is exploiting referential context into schema matching by introducing RACT learning and prediction, a self-supervised framework enabling the probabilistic retrieval of candidate tables for source columns to constrain relevant column candidates. Experiments demonstrate that this approach outperforms similarity-based baselines on matching multi-table schemas. In subsequent matching experiments, constraining the column search space via top-t tables improves both average matching precision and completeness by up to +70%.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 39 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

13 of 39 references.

References · 13

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2017Billion-scale similarity search with GPUscited by 2,497
  3. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  4. 2020Valentine: Evaluating Matching Techniques for Dataset Discoverycited by 35
  5. 2022SANTOS: Relationship-based Semantic Table Union Searchcited by 32
  6. 2024Magneto: Combining Small and Large Language Models for Schema Matchingcited by 17
  7. 2021PoWareMatch: a Quality-aware Deep Learning Approach to Improve Human Schema Matchingcited by 4
  8. 2022It's AI Match: A Two-Step Approach for Schema Matching Using Embeddingscited by 4
  9. 2020LEAPME: Learning-based Property Matching with Embeddingscited by 3
  10. 2024FREYJA: Efficient Join Discovery in Data Lakescited by 3
  11. 2025LLMATCH: A Unified Schema Matching Framework with Large Language Modelscited by 2
  12. 2016Living in Parallel Realities -- Co-Existing Schema Versions with a Bidirectional Database Evolution Languagecited by 1
1 more
  1. 2024SMUTF: Schema Matching Using Generative Tags and Hybrid Featurescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
  2. 2024RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph
  3. 2025RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
  4. 2026FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning
  5. 2025Improving Table Understanding with LLMs and Entity-Oriented Search
  6. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
  7. 2024Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
  8. 2026FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning