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

arXiv: https://arxiv.org/abs/2310.18208 · HTML: https://mlsanity.com/paper/2310.18208/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 69 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization](https://mlsanity.com/paper/2107.04649/) (2021)
- [OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization](https://mlsanity.com/paper/2212.12017/) (2022)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [GitTables: A Large-Scale Corpus of Relational Tables](https://mlsanity.com/paper/2106.07258/) (2021)
- [Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder](https://mlsanity.com/paper/2304.04052/) (2023)
- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [SANTOS: Relationship-based Semantic Table Union Search](https://mlsanity.com/paper/2209.13589/) (2022)
- [VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository](https://mlsanity.com/paper/1905.04616/) (2019)
- [CHORUS: Foundation Models for Unified Data Discovery and Exploration](https://mlsanity.com/paper/2306.09610/) (2023)
- [Learning Semantic Annotations for Tabular Data](https://mlsanity.com/paper/1906.00781/) (2019)

## Built on by (most cited first, 15 of 15)

- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Magneto: Combining Small and Large Language Models for Schema Matching](https://mlsanity.com/paper/2412.08194/) (2024)
- [mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs](https://mlsanity.com/paper/2312.02515/) (2023)
- [Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner](https://mlsanity.com/paper/2412.20662/) (2024)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph](https://mlsanity.com/paper/2409.14556/) (2024)
- [Graph Neural Network Approach to Semantic Type Detection in Tables](https://mlsanity.com/paper/2405.00123/) (2024)
- [LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues](https://mlsanity.com/paper/2507.13681/) (2025)
- [An LLM Agent-Based Complex Semantic Table Annotation Approach](https://mlsanity.com/paper/2508.12868/) (2025)
- [Accurate Table Question Answering with Accessible LLMs](https://mlsanity.com/paper/2601.03137/) (2026)
- [ZTab: Domain-based Zero-shot Annotation for Table Columns](https://mlsanity.com/paper/2603.11436/) (2026)
- [MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery](https://mlsanity.com/paper/2607.21781/) (2026)
- [Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAG](https://mlsanity.com/paper/2607.22319/) (2026)
- [Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data](https://mlsanity.com/paper/2609.38414/) (2026)

## Abstract (arXiv)

Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a large number of training samples per type and incur large run-time inference costs; and their performance can degrade when evaluated on novel datasets, even when types remain constant. Large language models have exhibited strong zero-shot classification performance on a wide range of tasks and in this paper we explore their use for CTA. We introduce ArcheType, a simple, practical method for context sampling, prompt serialization, model querying, and label remapping, which enables large language models to solve CTA problems in a fully zero-shot manner. We ablate each component of our method separately, and establish that improvements to context sampling and label remapping provide the most consistent gains. ArcheType establishes a new state-of-the-art performance on zero-shot CTA benchmarks (including three new domain-specific benchmarks which we release along with this paper), and when used in conjunction with classical CTA techniques, it outperforms a SOTA DoDuo model on the fine-tuned SOTAB benchmark. Our code is available at https://github.com/penfever/ArcheType.