# Column Type Annotation using ChatGPT arXiv: https://arxiv.org/abs/2306.00745 ยท HTML: https://mlsanity.com/paper/2306.00745/ ## Key facts - Cited by 19 papers in the map (data through 14 Oct 2026). - Builds on 23 of its 37 references that are in the map. - First posted on arXiv 1 Jun 2023. ## Builds on (most cited first, 23 of 23) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [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) - [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019) - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022) - [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022) - [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023) - [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022) - [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021) - [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019) - [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021) - [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022) - [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022) - [Instruction Induction: From Few Examples to Natural Language Task Descriptions](https://mlsanity.com/paper/2205.10782/) (2022) - [TABBIE: Pretrained Representations of Tabular Data](https://mlsanity.com/paper/2105.02584/) (2021) - [BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting](https://mlsanity.com/paper/2212.09535/) (2022) - [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019) - [Annotating Columns with Pre-trained Language Models](https://mlsanity.com/paper/2104.01785/) (2021) - [Dataset search: a survey](https://mlsanity.com/paper/1901.00735/) (2019) - [TCN: Table Convolutional Network for Web Table Interpretation](https://mlsanity.com/paper/2102.09460/) (2021) - [Using ChatGPT for Entity Matching](https://mlsanity.com/paper/2305.03423/) (2023) - [Data Lakes: A Survey of Functions and Systems](https://mlsanity.com/paper/2106.09592/) (2021) ## Built on by (most cited first, 19 of 19) - [Large Language Models and Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2308.06374/) (2023) - [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023) - [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025) - [TabLib: A Dataset of 627M Tables with Context](https://mlsanity.com/paper/2310.07875/) (2023) - [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023) - [Observatory: Characterizing Embeddings of Relational Tables](https://mlsanity.com/paper/2310.07736/) (2023) - [Knowledge Engineering using Large Language Models](https://mlsanity.com/paper/2310.00637/) (2023) - [RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph](https://mlsanity.com/paper/2409.14556/) (2024) - [Evaluating the Performance of ChatGPT for Spam Email Detection](https://mlsanity.com/paper/2402.15537/) (2024) - [Graph Neural Network Approach to Semantic Type Detection in Tables](https://mlsanity.com/paper/2405.00123/) (2024) - [Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs](https://mlsanity.com/paper/2503.09003/) (2025) - [Evaluating LLMs on Entity Disambiguation in Tables](https://mlsanity.com/paper/2408.06423/) (2024) - [An LLM Agent-Based Complex Semantic Table Annotation Approach](https://mlsanity.com/paper/2508.12868/) (2025) - [HySem: A context length optimized LLM pipeline for unstructured tabular extraction](https://mlsanity.com/paper/2408.09434/) (2024) - [High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services](https://mlsanity.com/paper/2504.17203/) (2025) - [Semantic Data Management in Data Lakes](https://mlsanity.com/paper/2310.15373/) (2023) - [ACCIO: Table Understanding Enhanced via Contrastive Learning with Aggregations](https://mlsanity.com/paper/2411.04443/) (2024) - [ZTab: Domain-based Zero-shot Annotation for Table Columns](https://mlsanity.com/paper/2603.11436/) (2026) - [Label Agreement Does Not Measure Authorization](https://mlsanity.com/paper/2610.04544/) (2026) ## Abstract (arXiv) Column type annotation is the task of annotating the columns of a relational table with the semantic type of the values contained in each column. Column type annotation is an important pre-processing step for data search and data integration in the context of data lakes. State-of-the-art column type annotation methods either rely on matching table columns to properties of a knowledge graph or fine-tune pre-trained language models such as BERT for column type annotation. In this work, we take a different approach and explore using ChatGPT for column type annotation. We evaluate different prompt designs in zero- and few-shot settings and experiment with providing task definitions and detailed instructions to the model. We further implement a two-step table annotation pipeline which first determines the class of the entities described in the table and depending on this class asks ChatGPT to annotate columns using only the relevant subset of the overall vocabulary. Using instructions as well as the two-step pipeline, ChatGPT reaches F1 scores of over 85% in zero- and one-shot setups. To reach a similar F1 score a RoBERTa model needs to be fine-tuned with 356 examples. This comparison shows that ChatGPT is able deliver competitive results for the column type annotation task given no or only a minimal amount of task-specific demonstrations.