PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions

• URL: http://arxiv.org/abs/2504.02112v2
• Date: Sat, 01 Nov 2025 07:15:26 GMT
• Title: PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions
• Authors: Renjie Liu, Haitian Jiang, Xiao Yan, Bo Tang, Jinyang Li,
• Abstract summary: We propose a complete four-class taxonomy to categorize the basic patterns of knowledge graph questions.<n>We then use it to create PolyBench, a new GraphRAG benchmark encompassing a comprehensive set of graph questions.<n>We propose PolyG, an adaptive GraphRAG approach by decomposing and categorizing the questions according to our proposed question taxonomy.
• Score: 12.124107412701173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: GraphRAG enhances large language models (LLMs) to generate quality answers for user questions by retrieving related facts from external knowledge graphs. However, current GraphRAG methods are primarily evaluated on and overly tailored for knowledge graph question answering (KGQA) benchmarks, which are biased towards a few specific question patterns and do not reflect the diversity of real-world questions. To better evaluate GraphRAG methods, we propose a complete four-class taxonomy to categorize the basic patterns of knowledge graph questions and use it to create PolyBench, a new GraphRAG benchmark encompassing a comprehensive set of graph questions. With the new benchmark, we find that existing GraphRAG methods fall short in effectiveness (i.e., quality of the generated answers) and/or efficiency (i.e., response time or token usage) because they adopt either a fixed graph traversal strategy or free-form exploration by LLMs for fact retrieval. However, different question patterns require distinct graph traversal strategies and context formation. To facilitate better retrieval, we propose PolyG, an adaptive GraphRAG approach by decomposing and categorizing the questions according to our proposed question taxonomy. Built on top of a unified interface and execution engine, PolyG dynamically prompts an LLM to generate a graph database query to retrieve the context for each decomposed basic question. Compared with SOTA GraphRAG methods, PolyG achieves a higher win rate in generation quality and has a low response latency and token cost. Our code and benchmark are open-source at https://github.com/Liu-rj/PolyG.

Related papers

• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching [61.824094419641575]
  Large Language Models (LLMs) struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA)<n>We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures.<n>Existing methods usually employ resource-intensive, non-scalable reasoning on vanilla KGs, but overlook this gap.<n>We propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries.
  arXiv  Detail & Related papers  (2025-09-25T06:48:52Z)
• When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation [25.508719115522645]
  Graph retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) with external knowledge.<n>Recent studies report that GraphRAG frequently underperforms vanilla RAG on many real-world tasks.<n>This raises a critical question: Is GraphRAG really effective, and in which scenarios do graph structures provide measurable benefits for RAG systems?
  arXiv  Detail & Related papers  (2025-06-06T02:37:47Z)
• GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation [26.654064783342545]
  Graph Retrieval Augmented Generation (GraphRAG) has garnered increasing recognition for its potential to enhance large language models (LLMs)<n>Current evaluations of GraphRAG models predominantly rely on traditional question-answering datasets.<n>We introduce GraphRAG-Bench, a large-scale, domain-specific benchmark designed to rigorously evaluate GraphRAG models.
  arXiv  Detail & Related papers  (2025-06-03T03:44:26Z)
• E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness [15.829377965705746]
  We propose E2GraphRAG, a streamlined graph-based RAG framework.<n>E2GraphRAG achieves up to 10 times faster indexing than GraphRAG and 100 times speedup over LightRAG in retrieval.
  arXiv  Detail & Related papers  (2025-05-30T05:27:40Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [75.9865035064794]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes [25.173078967881803]
  Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus. Current graph-based RAG approaches seldom prioritize the design of graph structures. Inadequately designed graph not only impede the seamless integration of diverse graph algorithms but also result in workflow inconsistencies. We propose NodeRAG, a graph-centric framework introducing heterogeneous graph structures.
  arXiv  Detail & Related papers  (2025-04-15T18:24:00Z)
• GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases [0.0]
  GraphRAFT is a retrieve-and-reason framework that finetunes LLMs to generate provably correct Cypher queries. Our method is the first such solution that can be taken off-the-shelf and used on Knowledge Graphs stored in native graph DBs.
  arXiv  Detail & Related papers  (2025-04-07T20:16:22Z)
• RAG vs. GraphRAG: A Systematic Evaluation and Key Insights [42.31801859160484]
  We systematically evaluate Retrieval-Augmented Generation (RAG) and GraphRAG on text-based benchmarks.<n>Our results highlight the distinct strengths of RAG and GraphRAG across different tasks and evaluation perspectives.
  arXiv  Detail & Related papers  (2025-02-17T02:36:30Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs) This framework provides a standardized setting to evaluate GNNs across diverse datasets. We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• Retrieval-Augmented Generation with Graphs (GraphRAG) [84.29507404866257]
  Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information.<n>Graph, by its intrinsic "nodes connected by edges" nature, encodes massive heterogeneous and relational information.<n>Unlike conventional RAG, the uniqueness of graph-structured data, such as diverse-formatted and domain-specific relational knowledge, poses unique and significant challenges when designing GraphRAG for different domains.
  arXiv  Detail & Related papers  (2024-12-31T06:59:35Z)
• Graph Retrieval-Augmented Generation: A Survey [28.979898837538958]
  Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation.
  arXiv  Detail & Related papers  (2024-08-15T12:20:24Z)
• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering [61.93058781222079]
  We develop a flexible question-answering framework targeting real-world textual graphs. We introduce the first retrieval-augmented generation (RAG) approach for general textual graphs. G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem.
  arXiv  Detail & Related papers  (2024-02-12T13:13:04Z)
• GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention [52.67633391931959]
  Graph invariant learning (GIL) has been an effective approach to discovering the invariant relationships between graph data and its labels. We propose a novel graph attention mechanism called Graph Sinkhorn Attention (GSINA) GSINA is able to obtain meaningful, differentiable invariant subgraphs with controllable sparsity and softness.
  arXiv  Detail & Related papers  (2024-02-11T12:57:16Z)
• From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited [51.24526202984846]
  Graph-based semi-supervised learning (GSSL) has long been a hot research topic.<n> graph convolutional networks (GCNs) have become the predominant techniques for their promising performance.<n>We propose three simple but powerful graph convolution methods.
  arXiv  Detail & Related papers  (2023-09-24T10:10:21Z)
• Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph [34.774049199809426]
  Knowledge graph question answering (i.e., KGQA) based on information retrieval aims to answer a question by retrieving answer from a large-scale knowledge graph. We first propose to partition the retrieved KSG to several smaller sub-KSGs via a new subgraph partition algorithm. We then present a graph-augmented learning to rank model to select the top-ranked sub-KSGs from them.
  arXiv  Detail & Related papers  (2021-11-20T08:27:37Z)
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction [123.20238648121445]
  We propose a new self-supervised learning framework, Graph Information Aided Node feature exTraction (GIANT) GIANT makes use of the eXtreme Multi-label Classification (XMC) formalism, which is crucial for fine-tuning the language model based on graph information. We demonstrate the superior performance of GIANT over the standard GNN pipeline on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-29T19:55:12Z)
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels? [89.13567439679709]
  Graph Identification (GI) has long been researched in graph learning and is essential in certain applications. This paper defines a novel problem dubbed Inverse Graph Identification (IGI) We propose a simple yet effective method that makes the node-level message passing process using Graph Attention Network (GAT) under the protocol of GI.
  arXiv  Detail & Related papers  (2020-07-12T12:06:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.