paper-with-me

Papers

Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning

2025-05-20 · Ruiyi Yang, Hao Xue, Imran Razzak, Hakim Hacid, Flora D. Salim

Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling to large knowledge graphs. Existing approaches often rely on monolithic graph retrieval, incurring unnecessary latency for simple queries and fragmented reasoning for complex multi-hop questions. To address these challenges, this paper propose SPLIT-RAG, a multi-agent RAG framework that addresses these limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval. The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG. The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types, while lightweight LLM agents are assigned to partitioned subgraphs, and only relevant partitions are activated during retrieval, thus reduce search space while enhancing efficiency. Finally, a hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications. Extensive experimental validation demonstrates considerable improvements compared to existing approaches.

📄 PDF Abstract BibTeX arXiv:2505.13994

Code (0)

등록된 구현이 없습니다.

Tasks

Attributegraph partitioningKnowledge GraphsRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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.
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 $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
WordPiece 설명 없음
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 &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources

2024-09-11 · Fomubad Borista Fondi, Azanzi Jiomekong Fidel, Gaoussou Camara

The Scholarly Hybrid Question Answering over Linked Data (QALD) Challenge at the International Semantic Web Conference (ISWC) 2024 focuses on Question Answering (QA) over diverse scholarly sources: DBLP, SemOpenAlex, and…

Extractive Question-AnsweringQuestion Answering

Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration

2025-05-27 · Sibo Xiao, Zixin Lin, Wenyang Gao, Yue Zhang

Processing long contexts has become a critical capability for modern large language models (LLMs). Existing works leverage agent-based divide-and-conquer methods for processing long contexts. But these methods face cruci…

RAG

Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models

2023-09-16 · Hossein Rajabzadeh, Suyuchen Wang, Hyock Ju Kwon, Bang Liu

We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions. In particular, we harness the power of large language models to divide a gi…

Multi-hop Question AnsweringQuestion Answering

DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs

2024-01-10 · Zijie Meng, Yan Zhang, Zhaopeng Feng, Zuozhu Liu

Large language models (LLMs) have shown impressive performance in reasoning benchmarks with the emergence of Chain-of-Thought (CoT), particularly in multi-choice question (MCQ). However, current works equally resolve que…

Question Answering

Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming

2024-02-29 · Hany Hamed, Subin Kim, Dongyeong Kim, Jaesik Yoon 외

Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strate…

Model-based Reinforcement Learning