mlsanityData to 7 Oct 2026

Don't Forget to Connect! Improving RAG with Graph-based Reranking

arXiv 2405.18414 ↗First posted 28 May 2024cs.CL cs.AI cs.LGcited by 49

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

Abstract (arXiv)

Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents. These systems work well when documents are clearly relevant to a question context. But what about when a document has partial information, or less obvious connections to the context? And how should we reason about connections between documents? In this work, we seek to answer these two core questions about RAG generation. We introduce G-RAG, a reranker based on graph neural networks (GNNs) between the retriever and reader in RAG. Our method combines both connections between documents and semantic information (via Abstract Meaning Representation graphs) to provide a context-informed ranker for RAG. G-RAG outperforms state-of-the-art approaches while having smaller computational footprint. Additionally, we assess the performance of PaLM 2 as a reranker and find it to significantly underperform G-RAG. This result emphasizes the importance of reranking for RAG even when using Large Language Models.

Key facts. Cited by 49 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 32 of its 45 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

32 of 45 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2017Graph Attention Networkscited by 8,854
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  8. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  9. 2018How Powerful are Graph Neural Networks?cited by 4,355
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  11. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  12. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
20 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  2. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  3. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  4. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  5. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  6. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  7. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  8. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 126
  9. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  10. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  11. 2022Re2G: Retrieve, Rerank, Generatecited by 102
  12. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 81
  13. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
  14. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 66
  15. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  16. 2017Improving Pairwise Ranking for Multi-label Image Classificationcited by 40
  17. 2021Semantic Representation for Dialogue Modelingcited by 24
  18. 2022Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answeringcited by 22
  19. 2021DocAMR: Multi-Sentence AMR Representation and Evaluationcited by 12
  20. 2023Exploiting Abstract Meaning Representation for Open-Domain Question Answeringcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 25; 2026: 14.

49 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insightscited by 51
  3. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  4. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  5. 2024On the Structural Memory of LLM Agentscited by 37
  6. 2024HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Basescited by 26
  7. 2025Empowering GraphRAG with Knowledge Filtering and Integrationcited by 15
  8. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  9. 2024Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphscited by 12
  10. 2025Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMscited by 12
  11. 2024OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answeringcited by 10
  12. 2024ShizishanGPT: An Agricultural Large Language Model Integrating Tools and Resourcescited by 9
37 more
  1. 2025Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generationcited by 9
  2. 2025CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoningcited by 9
  3. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  4. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Explorationcited by 7
  5. 2024SMART-RAG: Selection using Determinantal Matrices for Augmented Retrievalcited by 6
  6. 2025POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Modelscited by 6
  7. 2025Hybrid-NL2SVA: Integrating RAG and Finetuning for LLM-based NL2SVAcited by 5
  8. 2025A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChatcited by 5
  9. 2025SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMscited by 5
  10. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  11. 2025AcademicEval: Live Long-Context LLM Benchmarkcited by 4
  12. 2024What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QAcited by 3
  13. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challengescited by 3
  14. 2025The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Modelscited by 3
  15. 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chainscited by 3
  16. 2025Gumbel Reranking: Differentiable End-to-End Reranker Optimizationcited by 2
  17. 2025Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generationcited by 2
  18. 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layerscited by 2
  19. 2026DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answeringcited by 2
  20. 2026LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systemscited by 2
  21. 2025Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generationcited by 1
  22. 2025Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generationcited by 1
  23. 2025MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systemscited by 1
  24. 2026HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generationcited by 1
  25. 2024Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrievalcited by 0
  26. 2025Rethinking Data: Towards Better Performing Domain-Specific Small Language Modelscited by 0
  27. 2025Lightweight Relevance Grader in RAGcited by 0
  28. 2025Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Indexcited by 0
  29. 2026The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AIcited by 0
  30. 2026LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentationcited by 0
  31. 2026Why Retrieval-Augmented Generation Fails: A Graph Perspectivecited by 0
  32. 2026Active Learners as Efficient PRP Rerankerscited by 0
  33. 2026SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrievalcited by 0
  34. 2026Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesiscited by 0
  35. 2026CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generationcited by 0
  36. 2026BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrievalcited by 0
  37. 2026ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contractscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
  2. 2025In-depth Analysis of Graph-based RAG in a Unified Framework
  3. 2026NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation
  4. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  5. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  6. 2026Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?
  7. 2024Graph Retrieval-Augmented Generation: A Survey
  8. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey