mlsanityData to 7 Oct 2026

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

arXiv 2409.14556 ↗First posted 22 Sep 2024cs.DB cs.AIcited by 7

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

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.

Key facts. Cited by 7 papers in the map (data through 7 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.

Builds on

19 of 32 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  5. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  6. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  7. 2022Can Foundation Models Wrangle Your Data?cited by 173
  8. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  9. 2020MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Modelscited by 74
  10. 2022ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linkingcited by 74
  11. 2023MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Modelscited by 73
  12. 2021Annotating Columns with Pre-trained Language Modelscited by 37
7 more
  1. 2019Dataset search: a surveycited by 36
  2. 2023CHORUS: Foundation Models for Unified Data Discovery and Explorationcited by 24
  3. 2023Column Type Annotation using ChatGPTcited by 18
  4. 2023ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Modelscited by 15
  5. 2024SpreadsheetLLM: Encoding Spreadsheets for Large Language Modelscited by 15
  6. 2024EWEK-QA: Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systemscited by 13
  7. 2024KGLink: A column type annotation method that combines knowledge graph and pre-trained language modelcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  2. 2025Knowledge Graph-based Retrieval-Augmented Generation for Schema Matchingcited by 13
  3. 2026Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMscited by 9
  4. 2025Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuningcited by 1
  5. 2026Hippasus: Effective and Efficient Automatic Feature Augmentation for Machine Learning Tasks on Relational Datacited by 0
  6. 2026Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAGcited by 0
  7. 2026Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
  2. 2025Improving Table Understanding with LLMs and Entity-Oriented Search
  3. 2026RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching
  4. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
  5. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  6. 2024Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT
  7. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
  8. 2025RAKG:Document-level Retrieval Augmented Knowledge Graph Construction