Pith. sign in

REVIEW 27 cited by

GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.20139 v1 pith:TJFN5OIA submitted 2024-05-30 cs.CL cs.AIcs.LG

Costas Mavromatis , George Karypis This is my paper
classification cs.CLcs.AIcs.LG
keywords gnn-raggraphkgqalanguagereasoninganswerinformationnatural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Knowledge Graphs (KGs) represent human-crafted factual knowledge in the form of triplets (head, relation, tail), which collectively form a graph. Question Answering over KGs (KGQA) is the task of answering natural questions grounding the reasoning to the information provided by the KG. Large Language Models (LLMs) are the state-of-the-art models for QA tasks due to their remarkable ability to understand natural language. On the other hand, Graph Neural Networks (GNNs) have been widely used for KGQA as they can handle the complex graph information stored in the KG. In this work, we introduce GNN-RAG, a novel method for combining language understanding abilities of LLMs with the reasoning abilities of GNNs in a retrieval-augmented generation (RAG) style. First, a GNN reasons over a dense KG subgraph to retrieve answer candidates for a given question. Second, the shortest paths in the KG that connect question entities and answer candidates are extracted to represent KG reasoning paths. The extracted paths are verbalized and given as input for LLM reasoning with RAG. In our GNN-RAG framework, the GNN acts as a dense subgraph reasoner to extract useful graph information, while the LLM leverages its natural language processing ability for ultimate KGQA. Furthermore, we develop a retrieval augmentation (RA) technique to further boost KGQA performance with GNN-RAG. Experimental results show that GNN-RAG achieves state-of-the-art performance in two widely used KGQA benchmarks (WebQSP and CWQ), outperforming or matching GPT-4 performance with a 7B tuned LLM. In addition, GNN-RAG excels on multi-hop and multi-entity questions outperforming competing approaches by 8.9--15.5% points at answer F1.

Discussion (0). Sign in to comment.

Forward citations

Cited by 27 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

    cs.CL 2026-07 conditional novelty 7.0 of 10

    On a 28-tier nested enterprise corpus, BM25 becomes the most accurate scalable RAG retriever after ~10M tokens, beating an agentic file-search system by ~20 points at 601M tokens and remaining low-cost.

  2. DOTRAG: Retrieval-Time Reasoning Along Paths

    cs.IR 2026-04 unverdicted novelty 7.0 of 10

    DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.

  3. DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Decoupling macro topological routing from micro visual matching, plus query-driven GNN path decoding, improves multimodal multi-hop retrieval and QA over strong MM-RAG baselines.

  4. KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Partial-alignment contrastive pretraining plus anchor-then-expand graph retrieval improves multi-hop KG evidence recovery and downstream QA over strong dense and graph RAG baselines.

  5. BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

    cs.CL 2026-07 conditional novelty 6.0 of 10

    On an enterprise corpus scaled from 1.7M to 601M tokens, BM25 beats raw-file agentic search, dense retrieval, and graph RAG at large sizes, crossing near 10M tokens.

  6. TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation

    cs.IR 2026-07 conditional novelty 6.0 of 10

    TRIAGE instruments Graph-RAG with gold-free stage metrics and a usage-time diagnostic chain that localizes failures to extraction, graph/schema, or retrieval levers.

  7. SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and l...

  8. GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prio...

  9. EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming ...

  10. Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    A structured survey organizing graph-LLM integration methods by purpose, modality, and strategy across application domains.

  11. EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation

    cs.DB 2026-04 unverdicted novelty 6.0 of 10

    EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.

  12. AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM

    cs.CL 2025-10 unverdicted novelty 6.0 of 10

    AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.

  13. Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation

    cs.LG 2025-10 unverdicted novelty 6.0 of 10

    A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.

  14. Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

    cs.IR 2025-08 conditional novelty 6.0 of 10

    A schema-bounded agentic framework unifies graph construction and retrieval, reporting SOTA accuracy and up to 90.71% token-cost savings across six benchmarks, plus a new anonymized QA dataset.

  15. In-depth Analysis of Graph-based RAG in a Unified Framework

    cs.IR 2025-03 unverdicted novelty 6.0 of 10

    A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.

  16. ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation

    cs.IR 2025-02 unverdicted novelty 6.0 of 10

    ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.

  17. NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation

    cs.IR 2026-07 conditional novelty 5.0 of 10

    Combining Levenshtein, BM25, and GNN node matching with adaptive weights yields higher EM/F1 and win rates than NaiveRAG, GraphRAG, and LightRAG on multi-hop QA and long-context tasks.

  18. AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

    cs.IR 2026-06 unverdicted novelty 5.0 of 10

    AGE applies adaptive masking via a learnable sampler in Transformer-based SSL to align graph and text embeddings, yielding higher accuracy on four GraphQA benchmarks for non-parametric GraphRAG.

  19. S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    S³GNN mitigates oversquashing in message-passing networks via lightweight global mixing without strong prior assumptions, yielding up to 10x error reduction and 50% fewer parameters across multiple domains.

  20. From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    LOM-action uses business events to drive ontology-governed graph simulations that generate auditable decisions, reporting 93.82% accuracy and 98.74% tool-chain F1 versus 24-36% F1 for frontier LLMs.

  21. RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

    cs.CL 2025-10 unverdicted novelty 5.0 of 10

    RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.

  22. GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework

    cs.CL 2025-08 reject novelty 5.0 of 10

    GOSU globally merges semantic units from text chunks into a unit-centric knowledge graph and uses three-tier keyword retrieval to improve RAG generation quality, according to LLM-judge win rates.

  23. An Empirical Study of Multi-Agent RAG for Real-World University Admissions Counseling

    cs.SE 2025-07 conditional novelty 5.0 of 10

    A deployed multi-agent retrieval-augmented chatbot for Vietnamese university admissions achieved roughly 92% accuracy on over 6,000 real queries at a two-week cost of $11.58.

  24. Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

    cs.CL 2025-05 unverdicted novelty 5.0 of 10

    Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.

  25. Retrieval-Augmented Generation with Graphs (GraphRAG)

    cs.IR 2024-12 unverdicted novelty 5.0 of 10

    A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.

  26. Retrieval-Augmented Generation for AI-Generated Content: A Survey

    cs.CV 2024-02 accept novelty 5.0 of 10

    A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.

  27. Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs

    cs.AI 2025-09 reject novelty 4.0 of 10

    In a small comparative study, GraphRAG outscored spaCy and CoreNLP-based KG-QA pipelines on reasoning-heavy questions, but the evaluation design conflates method choice with pipeline architecture.

Pith tools