ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models

Summary: ArcheType uses LLMs for fully zero-shot column type annotation via context sampling, prompt serialization, and label remapping. It establishes new zero-shot SOTA, ships three domain benchmarks, and when combined with classical CTA beats fine-tuned DoDuo. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: hfb0d4b48d0af730a
Venue: VLDB
Year: 2024
Pagerank: 6.5144711e-05
Overall Rank: 4,589 | 69.15%
DOI: 10.14778/3665844.3665857

Incoming Non-self Citations Over Time

Authors

1. Benjamin Feuer (New York University)
2. Yurong Liu (New York University)
3. Chinmay Hegde (New York University)
4. Juliana Freire (New York University)

BibTeX Citation

@article{feuer_vldb24,
        title = {{ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models}},
        author = {Feuer, Benjamin and Liu, Yurong and Hegde, Chinmay and Freire, Juliana},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {9},
        pages = {2279--2292},
        doi = {10.14778/3665844.3665857},
        url = {https://doi.org/10.14778/3665844.3665857},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 14 of 14 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
4,218	Magneto: Combining Small and Large Language Models for Schema Matching	2025	VLDB	6.7270169e-05
8,887	mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs	2025	VLDB	5.2559789e-05
8,888	Optimized Batch Prompting for Cost-effective LLMs	2025	VLDB	5.2559789e-05
9,229	Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables	2025	SIGMOD	5.2056825e-05
10,165	Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding	2025	VLDB	5.0682654e-05
10,595	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD	4.9793485e-05
10,620	AutoDDG: Automated Dataset Description Generation using Large Language Models	2026	SIGMOD	4.9793485e-05
10,673	Qualitative Join Discovery in Data Lakes using Examples	2026	SIGMOD	4.9793485e-05
10,894	MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery	2026	VLDB	4.9793485e-05
11,038	Semantic Data Systems: From Data Management to Data Understanding	2026	VLDB	4.9793485e-05
11,189	Malleus: Straggler-Resilient Hybrid Parallel Training of Large-scale Models via Malleable Data and Model Parallelization	2025	SIGMOD	4.9793485e-05
11,303	LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation	2025	VLDB	4.9793485e-05
11,343	CoLA: Model Collaboration for Log-based Anomaly Detection	2025	VLDB	4.9793485e-05
11,423	Large Language Models for Spatial Analysis Queries	2025	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
89	WebTables: Exploring the Power of Tables on the Web	2008	VLDB	0.00035129658
95	Potter's Wheel: An Interactive Data Cleaning System	2001	VLDB	0.00034382643
329	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00020858443
377	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019570264
1,780	Annotating Columns with Pre-trained Language Models	2022	SIGMOD	9.6560923e-05
1,932	CHORUS: Foundation Models for Unified Data Discovery and Exploration	2024	VLDB	9.34643e-05
1,988	SANTOS: Relationship-based Semantic Table Union Search	2023	SIGMOD	9.2482448e-05
2,092	Sato: Contextual Semantic Type Detection in Tables	2020	VLDB	9.0626928e-05
2,521	GitTables: A Large-Scale Corpus of Relational Tables	2023	SIGMOD	8.3479333e-05
3,473	Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration	2023	SIGMOD	7.2728706e-05
5,106	Data-Driven Domain Discovery for Structured Datasets	2020	VLDB	6.2706946e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	7,012	Reliable Text-to-SQL with Adaptive Abstention	2025	SIGMOD
2	10,165	Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding	2025	VLDB
3	5,501	SemBench: A Benchmark for Semantic Query Processing Engines	2026	VLDB
4	5,100	Towards Benchmarking Feature Type Inference for AutoML Platforms	2021	SIGMOD
5	1,780	Annotating Columns with Pre-trained Language Models	2022	SIGMOD
6	8,594	RECA: Related Tables Enhanced Column Semantic Type Annotation Framework	2023	VLDB
7	2,092	Sato: Contextual Semantic Type Detection in Tables	2020	VLDB
8	6,488	Synthesizing Type-Detection Logic for Rich Semantic Data Types using Open-source Code	2018	SIGMOD
9	10,595	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD
10	3,489	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB