paper-with-me

Papers

PolyG: Effective and Efficient GraphRAG with Adaptive Graph Traversal

2025-04-02 · Renjie Liu, Haitian Jiang, Xiao Yan, Bo Tang, Jinyang Li

GraphRAG enhances large language models (LLMs) to generate quality answers for user questions by retrieving related facts from external knowledge graphs. Existing GraphRAG methods adopt a fixed graph traversal strategy for fact retrieval but we observe that user questions come in different types and require different graph traversal strategies. As such, existing GraphRAG methods are limited in effectiveness (i.e., quality of the generated answers) and/or efficiency (i.e., response time or the number of used tokens). In this paper, we propose to classify the questions according to a complete four-class taxonomy and adaptively select the appropriate graph traversal strategy for each type of questions. Our system PolyG is essentially a query planner for GraphRAG and can handle diverse questions with an unified interface and execution engine. Compared with SOTA GraphRAG methods, PolyG achieves an overall win rate of 75% on generation quality and a speedup up to 4x on response time.

📄 PDF Abstract BibTeX arXiv:2504.02112

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence

2026-04-18 · Andrea Volpini, Elie Raad arxiv

When does an LLM controller outperform rule-based traversal for knowledge graph exploration? We study this question through RLM-on-KG, a retrieval system that treats an LLM as an autonomous navigator over an RDF-encoded …

Question Answering

Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG

2026-05-14 · Riccardo Terrenzi, Maximilian von Zastrow, Serkan Ayvaz arxiv

Retrieval-Augmented Generation can improve factuality by grounding answers in external evidence, but Agentic GraphRAG complicates what it means for citations to be faithful. In these systems, an agent explores a knowledg…

Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scale

2025-07-04 · Congmin Min, Sahil Bansal, Joyce Pan, Abbas Keshavarzi 외 arxiv

We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval-Augmented Generation (GraphRAG) in enterprise environments. While GraphRAG has shown promise for multi- hop reasoning and structured …

Dependency Parsing

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs

2025-06-24 · Travis Thompson, Seung-Hwan Lim, Paul Liu, Ruoying He 외

Large Language Models (LLMs) have achieved impressive capabilities in language understanding and generation, yet they continue to underperform on knowledge-intensive reasoning tasks due to limited access to structured co…

Information RetrievalKnowledge GraphsMulti-hop Question AnsweringQuestion Answering+2

StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering

2025-10-03 · Tengjun Ni, Xin Yuan, Shenghong Li, Kai Wu 외 arxiv

Recent progress in retrieval-augmented generation (RAG) has led to more accurate and interpretable multi-hop question answering (QA). Yet, challenges persist in integrating iterative reasoning steps with external knowled…

Multi-hop Question AnsweringKnowledge Graphs