# RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph

arXiv: https://arxiv.org/abs/2409.14556 · HTML: https://mlsanity.com/paper/2409.14556/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 22 Sep 2024.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 19 of 19)

- [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)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Rethinking with Retrieval: Faithful Large Language Model Inference](https://mlsanity.com/paper/2301.00303/) (2022)
- [MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models](https://mlsanity.com/paper/2010.00840/) (2020)
- [ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking](https://mlsanity.com/paper/2207.04108/) (2022)
- [MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models](https://mlsanity.com/paper/2308.09729/) (2023)
- [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)
- [CHORUS: Foundation Models for Unified Data Discovery and Exploration](https://mlsanity.com/paper/2306.09610/) (2023)
- [Column Type Annotation using ChatGPT](https://mlsanity.com/paper/2306.00745/) (2023)
- [SpreadsheetLLM: Encoding Spreadsheets for Large Language Models](https://mlsanity.com/paper/2407.09025/) (2024)
- [ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models](https://mlsanity.com/paper/2310.18208/) (2023)
- [EWEK-QA: Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems](https://mlsanity.com/paper/2406.10393/) (2024)
- [KGLink: A column type annotation method that combines knowledge graph and pre-trained language model](https://mlsanity.com/paper/2406.00318/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching](https://mlsanity.com/paper/2501.08686/) (2025)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning](https://mlsanity.com/paper/2512.22742/) (2025)
- [Hippasus: Effective and Efficient Automatic Feature Augmentation for Machine Learning Tasks on Relational Data](https://mlsanity.com/paper/2602.02025/) (2026)
- [Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAG](https://mlsanity.com/paper/2607.22319/) (2026)
- [Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs](https://mlsanity.com/paper/2609.10430/) (2026)

## Abstract (arXiv)

As an important component of data exploration and integration, Column Type Annotation (CTA) aims to label columns of a table with one or more semantic types. With the recent development of Large Language Models (LLMs), researchers have started to explore the possibility of using LLMs for CTA, leveraging their strong zero-shot capabilities. In this paper, we build on this promising work and improve on LLM-based methods for CTA by showing how to use a Knowledge Graph (KG) to augment the context information provided to the LLM. Our approach, called RACOON, combines both pre-trained parametric and non-parametric knowledge during generation to improve LLMs' performance on CTA. Our experiments show that RACOON achieves up to a 0.21 micro F-1 improvement compared against vanilla LLM inference.