paper-with-me

Papers

HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation

2025-03-27 · Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Zemin Kuang, Meina Song, Yifan Zhu, Luu Anh Tuan

While standard Retrieval-Augmented Generation (RAG) based on chunks, GraphRAG structures knowledge as graphs to leverage the relations among entities. However, previous GraphRAG methods are limited by binary relations: one edge in the graph only connects two entities, which cannot well model the n-ary relations among more than two entities that widely exist in reality. To address this limitation, we propose HyperGraphRAG, a novel hypergraph-based RAG method that represents n-ary relational facts via hyperedges, modeling the complicated n-ary relations in the real world. To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism. Experiments across medicine, agriculture, computer science, and law demonstrate that HyperGraphRAG outperforms standard RAG and GraphRAG in accuracy and generation quality.

📄 PDF Abstract BibTeX arXiv:2503.21322

Code (1)

LHRLAB/HyperGraphRAG 공식 구현 pytorch

Tasks

RAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BART BART is a denoising autoencoder for pretraining sequence-to-sequence models. It is trained by (1) corrupting text…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation

2025-10-14 · Xiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu 외 arxiv

Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-b…

Multi-hop Question Answering

EEG-MedRAG: Enhancing EEG-based Clinical Decision-Making via Hierarchical Hypergraph Retrieval-Augmented Generation

2025-08-19 · Yi Wang, Haoran Luo, Lu Meng, Ziyu Jia 외 arxiv

With the widespread application of electroencephalography (EEG) in neuroscience and clinical practice, efficiently retrieving and semantically interpreting large-scale, multi-source, heterogeneous EEG data has become a p…

HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG

2026-01-25 · Jinyoung Park, Sanghyeok Lee, Omar Zia Khan, Hyunwoo J. Kim 외 arxiv

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform com…

Multi-hop Question AnsweringReinforcement LearningSemantic SimilarityKnowledge Graphs

Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models

2026-04-14 · Keshu Wu, Chenchen Kuai, Zihao Li, Jiwan Jiang 외 arxiv

Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including graph- and hypergraph-based approaches treat retrieved evidence as …

Question Answering

Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering

2025-08-15 · Changjian Wang, Weihong Deng, Weili Guan, Quan Lu 외 arxiv

Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer. Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grain…

Multi-hop Question AnsweringSemantic SimilarityAnswer GenerationKnowledge Graphs