Pith. sign in

REVIEW 16 cited by

GRAG: Graph Retrieval-Augmented Generation

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 2405.16506 v3 pith:QKBFLMUX submitted 2024-05-26 cs.LG

Yuntong Hu , Zhihan Lei , Zheng Zhang , Bo Pan , Chen Ling , Liang Zhao This is my paper
classification cs.LG
keywords graphgenerationgragtextualgraphsllmsretrieval-augmenteddocuments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs. To overcome this limitation, we introduce Graph Retrieval-Augmented Generation (GRAG), which tackles the fundamental challenges in retrieving textual subgraphs and integrating the joint textual and topological information into Large Language Models (LLMs) to enhance its generation. To enable efficient textual subgraph retrieval, we propose a novel divide-and-conquer strategy that retrieves the optimal subgraph structure in linear time. To achieve graph context-aware generation, incorporate textual graphs into LLMs through two complementary views-the text view and the graph view-enabling LLMs to more effectively comprehend and utilize the graph context. Extensive experiments on graph reasoning benchmarks demonstrate that in scenarios requiring multi-hop reasoning on textual graphs, our GRAG approach significantly outperforms current state-of-the-art RAG methods. Our datasets as well as codes of GRAG are available at https://github.com/HuieL/GRAG.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

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

  1. 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.

  2. Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

    cs.CL 2025-09 reject novelty 6.0 of 10

    SAT uses hierarchical contrastive alignment and a unified graph instruction to tune a lightweight adapter for knowledge graph completion, reporting large link prediction gains.

  3. 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.

  4. EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora

    cs.IR 2025-06 conditional novelty 6.0 of 10

    EraRAG uses hyperplane-based locality-sensitive hashing to build a hierarchical retrieval graph whose affected regions only are re-summarized when new documents arrive, cutting update cost by up to an order of magnitude.

  5. 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.

  6. How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A new GraphRAG evaluation framework using graph-grounded questions and bias-correction yields much smaller win rates than earlier reports, casting doubt on reported GraphRAG gains.

  7. CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution

    cs.CR 2025-05 conditional novelty 6.0 of 10

    CRAKEN, an LLM agent combining Self-RAG and Graph-RAG over a CTF writeup database, solves 22% of NYU CTF Bench challenges, three percentage points above the prior D-CIPHER baseline.

  8. 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.

  9. SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs

    cs.AI 2026-06 conditional novelty 5.0 of 10

    SCAIR, a training-free schema-conditioned agentic KG-RAG method, substantially outperforms existing KG-RAG approaches on a new enterprise CMDB benchmark, but the evaluation has notable confounds.

  10. KP-A: A Unified Network Knowledge Plane for Catalyzing Agentic Network Intelligence

    cs.NI 2025-07 conditional novelty 5.0 of 10

    KP-A is a proposed middleware knowledge plane that unifies live and static network knowledge for LLM agents in telecom networks, demonstrated on two simulated tasks.

  11. A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy

    cs.AI 2025-06 reject novelty 5.0 of 10

    A knowledge-graph-backed retrieval system for industrial waste questions outperforms standalone LLMs and naive RAG on six curated test cases, but the benchmark derives its ground truth from the same graph.

  12. 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.

  13. 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.

  14. REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing

    cs.AI 2025-10 conditional novelty 4.0 of 10

    A category-routed hybrid of RAG and knowledge-graph retrieval answers Vietnamese university-regulation questions with F1 98.89% on the authors' own dataset — about 0.2 points above plain RAG.

  15. TableVault: Managing Dynamic Data Collections for LLM-Augmented Workflows

    cs.DB 2025-06 reject novelty 4.0 of 10

    TableVault describes a system design for managing versioned, reproducible dataframe collections in LLM-augmented workflows, but it ships no implementation or evaluation.

  16. 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