OpenForge: Probabilistic Metadata Integration
Summary: Two-stage prior–posterior framework for metadata-concept alignment: fine-tuned LLMs and ensemble scorers produce priors over candidate relationships. A Markov Random Field refines them by maximizing joint assignment probability and encoding constraints (e.g., transitivity), achieving ≈25 F1 gain over GPT‑4. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Tianji Cong
- 2. Fatemeh Nargesian
- 3. Junjie Xing
- 4. H. V. Jagadish
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
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.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| Overall Rank | Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,791 | GalaxyWeaver: Autonomous Table-to-Graph Conversion and Schema Optimization with Large Language Models | 2025 | VLDB | 4.1905499e-05 |
| 2,422 | From Data Fusion to Knowledge Fusion | 2014 | VLDB | 8.8452901e-05 |
| 9,722 | Discovering and Ranking Semantic Associations over a Large RDF Metabase | 2004 | VLDB | 4.2917166e-05 |
| 3,626 | On-the-Fly Entity-Aware Query Processing in the Presence of Linkage | 2010 | VLDB | 6.9003552e-05 |
| 8,762 | Efficient Query Answering in Probabilistic RDF Graphs | 2011 | SIGMOD | 4.4520434e-05 |
| 9,179 | Efficient Exploration of Interesting Aggregates in RDF Graphs | 2021 | SIGMOD | 4.3793465e-05 |
| 7,027 | Mind the Data Gap: Bridging LLMs to Enterprise Data Integration | 2025 | CIDR | 4.8524216e-05 |
| 2,839 | Intensional Associations Between Data and Metadata | 2007 | SIGMOD | 8.0423129e-05 |
| 8,919 | Data Lakes Empowered by Knowledge Graph Technologies | 2021 | SIGMOD | 4.4229886e-05 |
| 1,179 | Table Union Search on Open Data | 2018 | VLDB | 0.00013458551 |