0% Complete
فارسی
Home
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
KGLM-QA: A Novel Approach for Knowledge Graph-Enhanced Large Language Models for Question Answering
Authors :
Alireza Akhavan safaei
1
Pegah Saboori
2
Reza Ramezani
3
Mohammadali Nematbakhsh
4
1- دانشگاه اصفهان
2- دانشگاه اصفهان
3- دانشگاه اصفهان
4- دانشگاه اصفهان
Keywords :
Large Language Models،Knowledge graph،Question Answering،Retrieval augmented generation
Abstract :
Large language models excel in various natural language processing tasks but often struggle with knowledge-intensive queries, particularly those involve rare entities or require precise factual information. This paper presents a novel framework that enhances capabilities of an LLM-based question answering system by incorporating structured knowledge from knowledge graphs. Our approach employs entity extraction, semantic similarity scoring, and adaptive graph exploration to efficiently navigate and extract relevant information from knowledge graphs. The core of the presented solution is a knowledge graph-enhanced language model process that iteratively refines subgraph exploration and answer generation, complemented by a fallback mechanism for robustness across diverse question types. Experiments on location-based questions from the Entity Questions dataset demonstrate significant improvements in the quality of responses. Using the Gemini 1.5 Flash model, our system achieved an accuracy increase from 36% to 71% for partially correct answers and from 22% to 69% for exactly correct answers, as evaluated by human assessors. This approach offers a promising direction for developing more reliable and accurate question answering systems, particularly for queries involving long-tail entities or specific factual knowledge.
Papers List
List of archived papers
سیستم توصیه گر برای خرید لوازم آرایشی و بهداشتی مبتنی بر الگوریتم جنگل تصادفی
فاطمه رمضانی خوزستانی - مجید رفیعی
ParaKavosh: A Parallel Algorithm for Finding Biological Network Motifs
Dr Zahra Razaghi Moghadam Kashani - Dr Ali Masoudi-nejad - Dr Abbas Nowzari-dalini
Integration of Electric Vehicles in Smart Grid using Deep Reinforcement Learning
Farkhondeh Kiaee
Stock Market Prediction Using Hard and Soft Data Fusion
Saeed Mohammadi Dashtaki - Masoud Alizadeh - Behzad Moshiri
3D Mesh ONoC: Design of low Insertion Loss and Non-blocking Optical Router and Efficient Routing Algorithm
Sanaz Asadinia - Elham Yaghoubi - Mostafa Sadeghi - Mahdi Mehrabi
A Demand Response Schema in Industry: Smart Scheduling Approach for Industrial Processes
Negin Shafinezhad - Hamid Abrishami - Maryam Mahmoodi
Enhancing Supervised Learning in Speech Emotion Recognition through Unsupervised Representations
Niloufar Faridani - Amirali Soltani Tehrani - Ramin Toosi
An ESB-based Architecture for Authentication as a Service Through Enterprise Application Integration
Masoumeh Hashemi - Mehdi Sakhaei-nia - Morteza Yousef Sanati
کشف لبه در تصاویر پزشکی با استفاده از اتوماتای سلولی سلسله مراتبی
مریم علینقی زاده - علیرضا رضوانیان
Improving Training Stability in Variational Autoencoders Through the Integration of Score Matching Loss
Amirreza Mokhtari Rad - Pouya Ardehkhani - Hormehr Alborzi
more
Samin Hamayesh - Version 41.3.1