mlsanityData to 14 Oct 2026

LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration

arXiv 2411.05844 ↗First posted 6 Nov 2024cs.AI cs.CL cs.DBcited by 7

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

GraphRAG integrates (knowledge) graphs with large language models (LLMs) to improve reasoning accuracy and contextual relevance. Despite its promising applications and strong relevance to multiple research communities, such as databases and natural language processing, GraphRAG currently lacks modular workflow analysis, systematic solution frameworks, and insightful empirical studies. To bridge these gaps, we propose LEGO-GraphRAG, a modular framework that enables: 1) fine-grained decomposition of the GraphRAG workflow, 2) systematic classification of existing techniques and implemented GraphRAG instances, and 3) creation of new GraphRAG instances. Our framework facilitates comprehensive empirical studies of GraphRAG on large-scale real-world graphs and diverse query sets, revealing insights into balancing reasoning quality, runtime efficiency, and token or GPU cost, that are essential for building advanced GraphRAG systems.

Key facts. Cited by 7 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 51 of its 113 references that are in the map. First posted on arXiv 6 Nov 2024.

Builds on

51 of 113 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models16 Oct
  2. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  4. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph15 Jul
  5. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec

Other references · 46

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  10. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  11. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  12. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
34 more
  1. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  2. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  3. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  4. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  6. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  7. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 301
  8. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  9. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  10. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 184
  11. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 171
  12. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  13. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  14. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  15. 2023Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answeringcited by 119
  16. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 101
  17. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  18. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 84
  19. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
  20. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  21. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  22. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 42
  23. 2019UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answeringcited by 37
  24. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  25. 2024Efficient Algorithms for Personalized PageRank Computation: A Surveycited by 21
  26. 2024GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understandingcited by 18
  27. 2020Personalized PageRank to a Target Node, Revisitedcited by 16
  28. 2024Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inferencecited by 16
  29. 2024Are Large Language Models the New Interface for Data Pipelines?cited by 13
  30. 2014FAST-PPR: Scaling Personalized PageRank Estimation for Large Graphscited by 6
  31. 2021Query-by-Sketch: Scaling Shortest Path Graph Queries on Very Large Networkscited by 3
  32. 2022Personalized PageRank on Evolving Graphs with an Incremental Index-Update Schemecited by 3
  33. 2021ThunderRW: An In-Memory Graph Random Walk Engine (Complete Version)cited by 2
  34. 2022Space-Efficient Random Walks on Streaming Graphscited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

7 papers.

  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  2. 2025BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documentscited by 16
  3. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoningcited by 8
  4. 2026When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Predictioncited by 0
  5. 2026AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generationcited by 0
  6. 2026GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG Methodscited by 0
  7. 2026GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scale
  2. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation
  3. 2026DOTRAG: Retrieval-Time Reasoning Along Paths
  4. 2025Empowering GraphRAG with Knowledge Filtering and Integration
  5. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
  6. 2025GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation
  7. 2025GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval
  8. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases