# Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective

arXiv: https://arxiv.org/abs/2410.17600 · HTML: https://mlsanity.com/paper/2410.17600/

## Key facts

- Cited by 12 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 28 of its 71 references that are in the map.
- First posted on arXiv 23 Oct 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, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations](https://mlsanity.com/paper/1511.02301/) (2015)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [Towards Building Multilingual Language Model for Medicine](https://mlsanity.com/paper/2402.13963/) (2024)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension](https://mlsanity.com/paper/2203.13947/) (2022)
- [GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs](https://mlsanity.com/paper/2305.12788/) (2023)
- [Unsupervised Statistical Machine Translation](https://mlsanity.com/paper/1809.01272/) (2018)
- [VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping](https://mlsanity.com/paper/2304.07810/) (2023)
- [Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction](https://mlsanity.com/paper/2307.01128/) (2023)
- [Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders](https://mlsanity.com/paper/2105.03505/) (2021)
- [Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts](https://mlsanity.com/paper/2308.10410/) (2023)
- [SyllabusQA: A Course Logistics Question Answering Dataset](https://mlsanity.com/paper/2403.14666/) (2024)
- [R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning](https://mlsanity.com/paper/2004.10610/) (2020)
- [PubGraph: A Large-Scale Scientific Knowledge Graph](https://mlsanity.com/paper/2302.02231/) (2023)
- [NNKGC: Improving Knowledge Graph Completion with Node Neighborhoods](https://mlsanity.com/paper/2302.06132/) (2023)
- [Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains](https://mlsanity.com/paper/2109.08722/) (2021)

## Built on by (most cited first, 12 of 12)

- [ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA](https://mlsanity.com/paper/2503.06951/) (2025)
- [MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph](https://mlsanity.com/paper/2508.12393/) (2025)
- [RAKG:Document-level Retrieval Augmented Knowledge Graph Construction](https://mlsanity.com/paper/2504.09823/) (2025)
- [Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems](https://mlsanity.com/paper/2601.14662/) (2026)
- [Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models](https://mlsanity.com/paper/2604.12185/) (2026)
- [Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine](https://mlsanity.com/paper/2503.16530/) (2025)
- [All-in-one Graph-based Indexing for Hybrid Search on GPUs](https://mlsanity.com/paper/2511.00855/) (2025)
- [Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge](https://mlsanity.com/paper/2601.10485/) (2026)
- [Capture-Calibrate-Coach: A Graph-Based Framework for Knowledge Monitoring Estimation and Adaptive Feedback](https://mlsanity.com/paper/2605.25419/) (2026)
- [CogGuard: Cognitive and Operational Profiling for Proactive Warning in Edge Intelligent Services](https://mlsanity.com/paper/2606.15199/) (2026)
- [Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs](https://mlsanity.com/paper/2606.29860/) (2026)
- [FashionKG-RAG: Knowledge Graph-Enhanced Retrieval-Augmented Generation for Fashion Question Answering](https://mlsanity.com/paper/2608.22688/) (2026)

## Abstract (arXiv)

Knowledge Graphs (KGs) are crucial in the field of artificial intelligence and are widely used in downstream tasks, such as question-answering (QA). The construction of KGs typically requires significant effort from domain experts. Large Language Models (LLMs) have recently been used for Knowledge Graph Construction (KGC). However, most existing approaches focus on a local perspective, extracting knowledge triplets from individual sentences or documents, missing a fusion process to combine the knowledge in a global KG. This work introduces Graphusion, a zero-shot KGC framework from free text. It contains three steps: in Step 1, we extract a list of seed entities using topic modeling to guide the final KG includes the most relevant entities; in Step 2, we conduct candidate triplet extraction using LLMs; in Step 3, we design the novel fusion module that provides a global view of the extracted knowledge, incorporating entity merging, conflict resolution, and novel triplet discovery. Results show that Graphusion achieves scores of 2.92 and 2.37 out of 3 for entity extraction and relation recognition, respectively. Moreover, we showcase how Graphusion could be applied to the Natural Language Processing (NLP) domain and validate it in an educational scenario. Specifically, we introduce TutorQA, a new expert-verified benchmark for QA, comprising six tasks and a total of 1,200 QA pairs. Using the Graphusion-constructed KG, we achieve a significant improvement on the benchmark, for example, a 9.2% accuracy improvement on sub-graph completion.