Pith. sign in

REVIEW 19 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 19 Pith papers

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

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

    cs.CL 2026-07 conditional novelty 7.0 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.

  2. 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.

  3. 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.

  4. 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.

  5. 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.

  6. KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendation

    cs.IR 2025-07 conditional novelty 6.0 of 10

    KERAG_R improves LLM-based top-k recommendation by using a GAT to select relevant KG triples and incorporating them into instruction-tuned prompts, reporting gains over ten baselines on three datasets.

  7. BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering

    cs.CL 2025-07 reject novelty 6.0 of 10

    BYOKG-RAG combines LLM-generated entities, paths, queries, and candidate answers with multiple graph retrieval tools to answer questions over custom knowledge graphs without training data.

  8. Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ReG refines weak graph-retriever supervision with LLM-selected reasoning chains and reorganizes retrieved triples into coherent evidence chains, improving KGQA accuracy, data efficiency, and reasoning token efficiency.

  9. Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RAPL combines LLM-rationalized path labels, line graph transformation, and path-based decoding to improve graph retrieval for KGQA, reporting state-of-the-art results on WebQSP and CWQ.

  10. BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions

    cs.CL 2025-06 conditional novelty 6.0 of 10

    BioMol-MQA is a new multimodal QA dataset for polypharmacy in which LLMs perform poorly zero-shot but much better when given gold context.

  11. 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.

  12. 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.

  13. 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.

  14. Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A multi-agent GraphRAG framework with self-reflection improves LLM accuracy on knowledge graph question answering.

  15. GPR: Empowering Generation with Graph-Pretrained Retriever

    cs.IR 2025-05 conditional novelty 5.0 of 10

    GPR pretrains a two-tower retriever on knowledge graphs using LLM-generated questions from masked triplets and a soft-preference triplet loss, improving KGQA accuracy across datasets and LLMs.

  16. Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Offline walks over a knowledge graph, verbalized into text and retrieved by embedding similarity, let a single LLM call answer multi-hop questions competitively without any fine-tuning.

  17. 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.

  18. LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

    cs.IR 2025-06 conditional novelty 4.0 of 10

    A KG-enhanced LlamaRec that feeds user-specific relation paths into a Llama-2 ranker reports modest MRR, NDCG, and Recall gains on two benchmarks.

  19. DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation

    cs.CL 2025-06 reject novelty 4.0 of 10

    A small model prompted with evidence and knowledge graphs generated by GPT-4o scores much higher on QA benchmarks, but the result is not true distillation and may be contaminated by teacher answer leakage.

Pith tools