Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration

Summary: Unicorn: a unified multi-task data-matching model for diverse integration tasks. A single Encoder+Matcher with mixture-of-experts enables cross-task knowledge sharing and zero-shot support across 20 datasets and 7 tasks, outperforming ad-hoc baselines. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h50c85e4d94ede4c2
Venue: SIGMOD
Year: 2023
Pagerank: 7.5597853e-05
Overall Rank: 3,166 | 78.78%
DOI: 10.1145/3588938

Incoming Non-self Citations Over Time

Authors

1. Jianhong Tu (Renmin University of China)
2. Ju Fan (Renmin University of China)
3. Nan Tang (Hong Kong University of Science and Technology; Qatar Computing Research Institute)
4. Peng Wang (Renmin University of China)
5. Guoliang Li (Tsinghua University)
6. Xiaoyong Du (Renmin University of China)
7. Xiaofeng Jia (Beijing Academy of Artificial Intelligence)
8. Song Gao (Beijing Academy of Artificial Intelligence)

BibTeX Citation

@inproceedings{tu_sigmod23,
        title = {{Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration}},
        author = {Tu, Jianhong and Fan, Ju and Tang, Nan and Wang, Peng and Li, Guoliang and Du, Xiaoyong and Jia, Xiaofeng and Gao, Song},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3588938},
        url = {https://dl.acm.org/doi/10.1145/3588938},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 17 of 17 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
1,669	Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks	2024	SIGMOD	9.9157758e-05
3,358	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB	7.3650961e-05
3,839	Automatic Database Configuration Debugging using Retrieval-Augmented Language Models	2025	SIGMOD	6.9704205e-05
4,047	Magneto: Combining Small and Large Language Models for Schema Matching	2025	VLDB	6.8177935e-05
4,335	ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models	2024	VLDB	6.6432811e-05
5,852	PreLog: A Pre-trained Model for Log Analytics	2024	SIGMOD	5.9526411e-05
7,076	How do Categorical Duplicates Affect ML? A New Benchmark and Empirical Analyses	2024	VLDB	5.5909675e-05
9,345	VerifAI: Verified Generative AI	2024	CIDR	5.1769528e-05
9,838	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD	5.1064323e-05
10,217	Progressive Entity Matching: A Design Space Exploration	2025	SIGMOD	5.0461625e-05
10,409	SemDistill: Bootstrapping a Low-Latency, Low-Cost Semantic Table Annotator from Noisy LLM	2027	SIGMOD	4.9605343e-05
10,412	Taxonomy Maintenance in the Wild over Evolving Scholarly Data: Reliability, Efficiency, and Cost-Effectiveness	2027	SIGMOD	4.9605343e-05
10,497	BEACON: Budget-Aware Entity Matching Across Domains	2026	SIGMOD	4.9605343e-05
11,242	A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces	2025	SIGMOD	4.9605343e-05
11,334	Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data Transformation	2025	VLDB	4.9605343e-05
11,358	OpenForge: Probabilistic Metadata Integration	2025	VLDB	4.9605343e-05
11,403	CoLA: Model Collaboration for Log-based Anomaly Detection	2025	VLDB	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 14 of 14 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
132	Deep Entity Matching with Pre-Trained Language Models	2021	VLDB	0.00030213215
158	Deep Learning for Entity Matching: A Design Space Exploration	2018	SIGMOD	0.00028049555
323	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00021022156
366	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019902067
399	COMA - A system for flexible combination of schema matching approaches	2002	VLDB	0.00019094502
459	Distributed Representations of Tuples for Entity Resolution	2018	VLDB	0.00017863654
972	The Data Civilizer System	2017	CIDR	0.00012742827
1,358	Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes	2023	CIDR	0.00010902306
1,650	Falcon: Scaling Up Hands-Off Crowdsourced Entity Matching to Build Cloud Services	2017	SIGMOD	9.9690948e-05
2,216	Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning	2023	SIGMOD	8.8249841e-05
2,520	Deep Learning for Blocking in Entity Matching: A Design Space Exploration	2021	VLDB	8.3343971e-05
3,822	Trie-Join: Efficient Trie-based String Similarity Joins with Edit-Distance Constraints	2010	VLDB	6.9814064e-05
4,080	Smurf: Self-Service String Matching Using Random Forests	2019	VLDB	6.8020845e-05
5,830	Domain Adaptation for Deep Entity Resolution	2022	SIGMOD	5.9627079e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,908	Unify: A System For Unstructured Data Analytics	2025	VLDB
2	5,830	Domain Adaptation for Deep Entity Resolution	2022	SIGMOD
3	6,404	Human-in-the-loop Data Integration	2017	VLDB
4	4,613	Reducing Uncertainty of Schema Matching via Crowdsourcing	2013	VLDB
5	9,203	Analyzing and Revising Data Integration Schemas to Improve Their Matchability	2008	VLDB
6	10,539	Generalized Entity Matching with Adaptivity via Large Language Models	2026	SIGMOD
7	11,788	Splitting Tuples of Mismatched Entities	2023	SIGMOD
8	9,214	Entity Matching in the Wild: A Consistent and Versatile Framework to Unify Data in Industrial Applications	2020	SIGMOD
9	9,823	The Battleship Approach to the Low Resource Entity Matching Problem	2023	SIGMOD
10	1,348	Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks	2020	SIGMOD