홈 › Papers

GeAR: Graph-enhanced Agent for Retrieval-augmented Generation

2024-12-24 · Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Damien Graux, Dandan Tu, Zeren Jiang, Ruofei Lai, Yang Ren, Jeff Z. Pan

Retrieval-augmented generation systems rely on effective document retrieval capabilities. By design, conventional sparse or dense retrievers face challenges in multi-hop retrieval scenarios. In this paper, we present GeAR, which advances RAG performance through two key innovations: (i) graph expansion, which enhances any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates graph expansion. Our evaluation demonstrates GeAR's superior retrieval performance on three multi-hop question answering datasets. Additionally, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while requiring fewer tokens and iterations compared to other multi-step retrieval systems.

📄 PDF Abstract BibTeX arXiv:2412.18431

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-hop Question Answering Question Answering RAG RetrievalRetrieval-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…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

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…

Residual Connection 설명 없음

Adam 설명 없음

RAGEAR: Retrieval-Augmented Graph-Enhanced Academic Recommender

2026-05-26 · Francesco Granata, Lorenzo Lamazzi, Misael Mongiovì, Francesco Poggi 외 arxiv

We present RAGEAR (Retrieval-Augmented Graph-Enhanced Academic Recommender), a neurosymbolic recommender system for academic course recommendation. RAGEAR combines dense retrieval over full lecture transcripts with a sym…

FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval

2025-09-15 · Ying Li, Mengyu Wang, Miguel de Carvalho, Sotirios Sabanis 외 arxiv

Financial disclosures such as 10-K filings present challenging retrieval problems due to their length, regulatory section hierarchy, and domain-specific language, which standard retrieval-augmented generation (RAG) model…

Millions of $\text{GeAR}$-s: Extending GraphRAG to Millions of Documents

2025-07-23 · Zhili Shen, Chenxin Diao, Pascual Merita, Pavlos Vougiouklis 외 arxiv

Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance r…

Multi-hop Question Answering

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

2025-07-29 · Haoran Luo, Haihong E, Guanting Chen, Qika Lin 외 arxiv

Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling know…

Reinforcement Learning

GeAR: Generation Augmented Retrieval

2025-01-06 · Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan 외

Document retrieval techniques form the foundation for the development of large-scale information systems. The prevailing methodology is to construct a bi-encoder and compute the semantic similarity. However, such scalar …

Retrieval Semantic Similarity Semantic Textual Similarity