OpenForge: Probabilistic Metadata Integration

Summary: OpenForge integrates heterogeneous metadata concepts via a two-stage prior–posterior framework: LLM-based candidate beliefs refined by MRF inference encoding constraints such as transitivity. Outperforms GPT-4 by 25 F1 points on vocabulary matching. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 14118
Venue: VLDB
Year: 2025
Pagerank: 5.093636e-05
Overall Rank: 10,897 | 25.24%
DOI: 10.14778/3746405.3746417

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Tianji Cong (University of Michigan)
2. Fatemeh Nargesian (University of Rochester)
3. Junjie Xing (University of Michigan)
4. H. V. Jagadish (University of Michigan)

BibTeX Citation

@article{cong_vldb25,
        title = {{OpenForge: Probabilistic Metadata Integration}},
        author = {Cong, Tianji and Nargesian, Fatemeh and Xing, Junjie and Jagadish, H. V.},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {9},
        pages = {2914--2927},
        doi = {10.14778/3746405.3746417},
        url = {https://doi.org/10.14778/3746405.3746417},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 15 of 15 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
141	Deep Entity Matching with Pre-Trained Language Models	2021	VLDB	0.0002964847
176	Deep Learning for Entity Matching: A Design Space Exploration	2018	SIGMOD	0.00027191081
390	COMA - A system for flexible combination of schema matching approaches	2002	VLDB	0.00019382486
514	Goods: Organizing Google's Datasets	2016	SIGMOD	0.00017178673
749	Data Lake Management: Challenges and Opportunities	2019	VLDB	0.00014379989
878	Table Union Search on Open Data	2018	VLDB	0.00013463374
1,447	Auctus: A Dataset Search Engine for Data Discovery and Augmentation	2021	VLDB	0.00010760327
2,315	SANTOS: Relationship-based Semantic Table Union Search	2023	SIGMOD	8.7605101e-05
3,436	Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration	2023	SIGMOD	7.4157897e-05
3,456	Automatic Discovery of Attributes in Relational Databases	2011	SIGMOD	7.3998323e-05
4,935	Querying Probabilistic Information Extraction	2010	VLDB	6.4357418e-05
5,513	Foundations of Uncertain-Data Integration	2010	VLDB	6.1909879e-05
5,956	RONIN: Data Lake Exploration	2021	VLDB	6.0287066e-05
7,325	ADnEV: Cross-Domain Schema Matching using Deep Similarity Matrix Adjustment and Evaluation	2020	VLDB	5.6443833e-05
8,144	WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses	2023	CIDR	5.4800625e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,014	GalaxyWeaver: Autonomous Table-to-Graph Conversion and Schema Optimization with Large Language Models	2025	VLDB
2	2,351	From Data Fusion to Knowledge Fusion	2014	VLDB
3	9,859	Discovering and Ranking Semantic Associations over a Large RDF Metabase	2004	VLDB
4	3,514	On-the-Fly Entity-Aware Query Processing in the Presence of Linkage	2010	VLDB
5	8,935	Efficient Query Answering in Probabilistic RDF Graphs	2011	SIGMOD
6	9,339	Efficient Exploration of Interesting Aggregates in RDF Graphs	2021	SIGMOD
7	7,228	Mind the Data Gap: Bridging LLMs to Enterprise Data Integration	2025	CIDR
8	4,095	Intensional Associations Between Data and Metadata	2007	SIGMOD
9	9,071	Data Lakes Empowered by Knowledge Graph Technologies	2021	SIGMOD
10	878	Table Union Search on Open Data	2018	VLDB