0% Complete
فارسی
Home
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Knowledge Graph Based Retrieval-Augmented Generation for Multi-Hop Question Answering Enhancement
Authors :
Mahdi Amiri Shavaki
1
Pouria Omrani
2
Ramin Toosi
3
Mohammad Ali Akhaee
4
1- دانشکده برق و کامپیوتر دانشگاه تهران
2- دانشگاه صنعتی خواجه نصیرالدین طوسی
3- دانشکده برق و کامپیوتر دانشگاه تهران
4- دانشکده برق و کامپیوتر دانشگاه تهران
Keywords :
Graph RAG،Generative AI،LLM،Multi-hop QA،NLP
Abstract :
Multi-hop question answering (QA), which requires integrating information from multiple sources, poses significant challenges in natural language processing. Existing methods often struggle with effective retrieval across documents, leading to incomplete or inaccurate answers. Building upon Graph-based Retrieval-Augmented Generation (Graph RAG), we enhance multi-hop QA by leveraging structured knowledge graphs. Specifically, we construct individual knowledge graphs for each document, where entities are represented as nodes and the relationships between them as edges enriched with contextual properties. These individual graphs are then seamlessly integrated into a comprehensive, unified graph that captures cross-document relationships. Our method improves retrieval by utilizing vector embeddings of these graph relations, enabling more effective multi-hop reasoning across the interconnected data. To evaluate our approach, we assembled a dataset of 500 documents paired with 296 multi-hop questions requiring cross-document information retrieval. Our contributions include developing a novel graph-based retrieval mechanism that leverages vector embeddings of graph relations within the Graph RAG framework, and assembling a comprehensive dataset for multi-hop QA. Comparative experiments show that our enhanced Graph RAG method significantly outperforms the baseline in factual accuracy and semantic similarity, as measured by the RAGAS framework. Additionally, an LLM-based evaluator highlights our method's superior performance in answer comprehensiveness, empowerment, and directness.
Papers List
List of archived papers
بهبود رهگیری در زنجیره تامین با استفاده از فناوری زنجیره بلوکی
سید عماد موسوی - مهرداد آشتیانی
Persian Language Understanding in Task-oriented Dialogue System for Online Shopping
Zeinab Borhanifard - Hossein Basafa - Seyedeh Zahra Razavi - Heshaam Faili
Improving Training Stability in Variational Autoencoders Through the Integration of Score Matching Loss
Amirreza Mokhtari Rad - Pouya Ardehkhani - Hormehr Alborzi
LLM-Driven Feature Extraction for Stock Market Prediction: A case study of Tehran Stock Exchange
Siavash Hosseinpour Saffarian - Saman Haratizadeh
Optimal control of robotic hand for rehabilitation using fractional order systems and EEG signal processing
Mehran Safari Dehnavi - Vahid Safari Dehnavi - Masoud Shafiee
Evaluating LLMs in Persian News Summarization
Arya VarastehNezhad - Reza Tavasoli - Mostafa Masumi - Seyed Soroush Majd - Mehrnoush Shamsfard
Enhancing kNN-Based Intrusion Detection with Differential Evolution with Auto-Enhanced Population Diversity
Zohre Karimi - Zeinab Torabi
Classification of mental states of human concentration based on EEG signal
Mehran Safari Dehnavi - Vahid Safari Dehnavi - Dr Masoud Shafiee
AI-Driven Approach to Detect Equivalent Elements within Domain Models
Mohammad-Sajad Kasaei - Mohammadreza Sharbaf - Afsaneh Fatemi - Bahman Zamani
Effective Design of Reversible 2×2 Vedic Multiplier With Low Cost
Mojtaba Noorallahzadeh - Mohammad Mosleh - Ali Shahidikia
more
Samin Hamayesh - Version 41.3.1