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: 13459
Venue: VLDB
Year: 2024
Pagerank: 5.6943033e-05
Overall Rank: 5,098 | 64.57%
DOI: 10.14778/3665844.3665857

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 12 of 12 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,045	Magneto: Combining Small and Large Language Models for Schema Matching	2025	VLDB	4.8474104e-05
8,518	mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs	2025	VLDB	4.4893996e-05
10,109	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD	4.1905499e-05
10,142	AutoDDG: Automated Dataset Description Generation using Large Language Models	2026	SIGMOD	4.1905499e-05
10,197	Qualitative Join Discovery in Data Lakes using Examples	2026	SIGMOD	4.1905499e-05
10,502	Malleus: Straggler-Resilient Hybrid Parallel Training of Large-scale Models via Malleable Data and Model Parallelization	2025	SIGMOD	4.1905499e-05
10,521	Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables	2025	SIGMOD	4.1905499e-05
10,603	Optimized Batch Prompting for Cost-effective LLMs	2025	VLDB	4.1905499e-05
10,666	LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation	2025	VLDB	4.1905499e-05
10,720	CoLA: Model Collaboration for Log-based Anomaly Detection	2025	VLDB	4.1905499e-05
10,759	Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding	2025	VLDB	4.1905499e-05
10,839	Large Language Models for Spatial Analysis Queries	2025	VLDB	4.1905499e-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
108	WebTables: Exploring the Power of Tables on the Web	2008	VLDB	0.00048345996
112	Potter's Wheel: An Interactive Data Cleaning System	2001	VLDB	0.00047010908
514	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00021280726
516	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00021194444
2,513	Annotating Columns with Pre-trained Language Models	2022	SIGMOD	8.6155767e-05
2,895	Sato: Contextual Semantic Type Detection in Tables	2020	VLDB	7.9539265e-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
3,520	GitTables: A Large-Scale Corpus of Relational Tables	2023	SIGMOD	7.0136102e-05
4,211	Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration	2023	SIGMOD	6.3495931e-05
5,538	Data-Driven Domain Discovery for Structured Datasets	2020	VLDB	5.4520759e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
7,351	Reliable Text-to-SQL with Adaptive Abstention	2025	SIGMOD	4.7484027e-05
10,759	Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding	2025	VLDB	4.1905499e-05
10,277	SemBench: A Benchmark for Semantic Query Processing Engines	2026	VLDB	4.1905499e-05
5,244	Towards Benchmarking Feature Type Inference for AutoML Platforms	2021	SIGMOD	5.6021738e-05
2,513	Annotating Columns with Pre-trained Language Models	2022	SIGMOD	8.6155767e-05
8,576	RECA: Related Tables Enhanced Column Semantic Type Annotation Framework	2023	VLDB	4.4879383e-05
2,895	Sato: Contextual Semantic Type Detection in Tables	2020	VLDB	7.9539265e-05
6,411	Synthesizing Type-Detection Logic for Rich Semantic Data Types using Open-source Code	2018	SIGMOD	5.0675656e-05
10,109	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD	4.1905499e-05
4,908	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB	5.835596e-05