mlsanityData to 14 Oct 2026

Empowering GraphRAG with Knowledge Filtering and Integration

arXiv 2503.13804 ↗First posted 18 Mar 2025cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

In recent years, large language models (LLMs) have revolutionized the field of natural language processing. However, they often suffer from knowledge gaps and hallucinations. Graph retrieval-augmented generation (GraphRAG) enhances LLM reasoning by integrating structured knowledge from external graphs. However, we identify two key challenges that plague GraphRAG:(1) Retrieving noisy and irrelevant information can degrade performance and (2)Excessive reliance on external knowledge suppresses the model's intrinsic reasoning. To address these issues, we propose GraphRAG-FI (Filtering and Integration), consisting of GraphRAG-Filtering and GraphRAG-Integration. GraphRAG-Filtering employs a two-stage filtering mechanism to refine retrieved information. GraphRAG-Integration employs a logits-based selection strategy to balance external knowledge from GraphRAG with the LLM's intrinsic reasoning,reducing over-reliance on retrievals. Experiments on knowledge graph QA tasks demonstrate that GraphRAG-FI significantly improves reasoning performance across multiple backbone models, establishing a more reliable and effective GraphRAG framework.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

22 of 38 references.

References · 22

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  4. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  5. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  7. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  8. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)cited by 159
  9. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  10. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  11. 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinementscited by 103
  12. 2023Overthinking the Truth: Understanding how Language Models Process False Demonstrationscited by 81
10 more
  1. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  2. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  3. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  4. 2024TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attentioncited by 29
  5. 2024Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layerscited by 25
  6. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systemscited by 23
  7. 2024Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspectivecited by 20
  8. 2025SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidencecited by 18
  9. 2023Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoningcited by 16
  10. 2025Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approachcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 48
  2. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structurescited by 23
  3. 2025Semantic Energy: Detecting LLM Hallucination Beyond Entropycited by 18
  4. 2025Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphscited by 6
  5. 2025Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generationcited by 5
  6. 2025How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptationcited by 4
  7. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generationcited by 3
  8. 2026Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Explorationcited by 3
  9. 2026TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learningcited by 1
  10. 2026DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understandingcited by 1
  11. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAGcited by 0
  12. 2026Why Retrieval-Augmented Generation Fails: A Graph Perspectivecited by 0
3 more
  1. 2026AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generationcited by 0
  2. 2026LivingRAG: Augmenting Graph RAG with Experiencecited by 0
  3. 2026Beyond Similarity through Zero-Token Geometric Graphs for Multi-Hop RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration
  2. 2026RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
  3. 2026GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
  4. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
  5. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases
  6. 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
  7. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  8. 2025Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scale