Back to papers
Magneto: Combining Small and Large Language Models for Schema Matching
Summary: Magneto uses a two-phase retrieval+reranking pipeline that leverages cheap small LMs to generate candidates and powerful LLMs to rerank, trading minimal compute for high matching accuracy. Novel contributions: LLM-synthesized self-supervised SLM fine-tuning, effective reranking prompts, and a challenging biomedical benchmark.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 13912
- Venue
- VLDB
- Year
- 2025
- Pagerank
- 4.8474104e-05
- Overall Rank
- 7,045 | 51.04%
- DOI
-
10.14778/3742728.3742757
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 304 |
Generic Schema Matching with Cupid |
2001 |
VLDB |
0.00028282278 |
| 383 |
COMA - A system for flexible combination of schema matching approaches |
2002 |
VLDB |
0.00024802484 |
| 516 |
Can Foundation Models Wrangle Your Data? |
2023 |
VLDB |
0.00021194444 |
| 519 |
Data Integration for the Relational Web |
2009 |
VLDB |
0.00021148006 |
| 968 |
Schema and Ontology Matching with COMA++ |
2005 |
SIGMOD |
0.00014941789 |
| 1,914 |
Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks |
2020 |
SIGMOD |
0.00010111859 |
| 2,513 |
Annotating Columns with Pre-trained Language Models |
2022 |
SIGMOD |
8.6155767e-05 |
| 2,585 |
Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks |
2024 |
SIGMOD |
8.4909917e-05 |
| 2,737 |
Open Data Integration |
2018 |
VLDB |
8.2053894e-05 |
| 2,842 |
Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning |
2023 |
VLDB |
8.0366354e-05 |
| 3,001 |
SANTOS: Relationship-based Semantic Table Union Search |
2023 |
SIGMOD |
7.739698e-05 |
| 3,003 |
Chorus: Foundation Models for Unified Data Discovery and Exploration |
2024 |
VLDB |
7.7358219e-05 |
| 3,326 |
DeepJoin: Joinable Table Discovery with Pre-trained Language Models |
2023 |
VLDB |
7.2148323e-05 |
| 3,826 |
Automatic Discovery of Attributes in Relational Databases |
2011 |
SIGMOD |
6.7204879e-05 |
| 4,211 |
Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration |
2023 |
SIGMOD |
6.3495931e-05 |
| 5,098 |
ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models |
2024 |
VLDB |
5.6943033e-05 |
| 5,457 |
Transformers for Tabular Data Representation: A Tutorial on Models and Applications |
2022 |
VLDB |
5.4960654e-05 |
| 5,949 |
Top-K Generation of Integrated Schemas Based on Directed and Weighted Correspondences |
2009 |
SIGMOD |
5.2564001e-05 |
| 7,614 |
ADnEV: Cross-Domain Schema Matching using Deep Similarity Matrix Adjustment and Evaluation |
2020 |
VLDB |
4.6916018e-05 |
| 11,028 |
Sampling Methods for Inner Product Sketching |
2024 |
VLDB |
4.1905499e-05 |
Semantically Similar Papers