# RAKG:Document-level Retrieval Augmented Knowledge Graph Construction

arXiv: https://arxiv.org/abs/2504.09823 · HTML: https://mlsanity.com/paper/2504.09823/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [BERT for Coreference Resolution: Baselines and Analysis](https://mlsanity.com/paper/1908.09091/) (2019)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [A Comprehensive Survey on Automatic Knowledge Graph Construction](https://mlsanity.com/paper/2302.05019/) (2023)
- [KGGen: Extracting Knowledge Graphs from Plain Text with Language Models](https://mlsanity.com/paper/2502.09956/) (2025)
- [Classifying Relations by Ranking with Convolutional Neural Networks](https://mlsanity.com/paper/1504.06580/) (2015)
- [SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs](https://mlsanity.com/paper/2410.02811/) (2024)
- [KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment](https://mlsanity.com/paper/2502.06472/) (2025)
- [PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation](https://mlsanity.com/paper/2501.11551/) (2025)
- [DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population](https://mlsanity.com/paper/2201.03335/) (2022)
- [Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective](https://mlsanity.com/paper/2410.17600/) (2024)
- [Graph Refinement for Coreference Resolution](https://mlsanity.com/paper/2203.16574/) (2022)

## Built on by (most cited first, 4 of 4)

- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework](https://mlsanity.com/paper/2509.00449/) (2025)
- [The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI](https://mlsanity.com/paper/2603.06290/) (2026)
- [TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation](https://mlsanity.com/paper/2607.03447/) (2026)

## Abstract (arXiv)

With the rise of knowledge graph based retrieval-augmented generation (RAG) techniques such as GraphRAG and Pike-RAG, the role of knowledge graphs in enhancing the reasoning capabilities of large language models (LLMs) has become increasingly prominent. However, traditional Knowledge Graph Construction (KGC) methods face challenges like complex entity disambiguation, rigid schema definition, and insufficient cross-document knowledge integration. This paper focuses on the task of automatic document-level knowledge graph construction. It proposes the Document-level Retrieval Augmented Knowledge Graph Construction (RAKG) framework. RAKG extracts pre-entities from text chunks and utilizes these pre-entities as queries for RAG, effectively addressing the issue of long-context forgetting in LLMs and reducing the complexity of Coreference Resolution. In contrast to conventional KGC methods, RAKG more effectively captures global information and the interconnections among disparate nodes, thereby enhancing the overall performance of the model. Additionally, we transfer the RAG evaluation framework to the KGC field and filter and evaluate the generated knowledge graphs, thereby avoiding incorrectly generated entities and relationships caused by hallucinations in LLMs. We further developed the MINE dataset by constructing standard knowledge graphs for each article and experimentally validated the performance of RAKG. The results show that RAKG achieves an accuracy of 95.91 % on the MINE dataset, a 6.2 % point improvement over the current best baseline, GraphRAG (89.71 %). The code is available at https://github.com/LMMApplication/RAKG.