0% Complete
فارسی
Home
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Context Awareness Gate for Retrieval Augmented Generation
Authors :
Mohammad Hassan Heydari
1
Arshia Hemmat
2
Erfan Naman
3
Afsaneh Fatemi
4
1- دانشگاه اصفهان
2- دانشگاه اصفهان
3- دانشگاه اصفهان
4- دانشگاه اصفهان
Keywords :
Retrieval-Augmented Generation،Hallucination،Large Language Models،Open Domain Question Answering
Abstract :
Retrieval-augmented generation (RAG) has emerged as a widely adopted approach to mitigate the limitations of large language models (LLMs) in answering domain-specific questions. Previous research has predominantly focused on improving the accuracy and quality of retrieved data chunks to enhance the overall performance of the generation pipeline. However, despite ongoing advancements, the critical issue of retrieving irrelevant information—which can impair a model’s ability to utilize its internal knowledge effectively—has received minimal attention. In this work, we investigate the impact of retrieving irrelevant information in open-domain question answering, highlighting its significant detrimental effect on the quality of LLM outputs. To address this challenge, we propose the Context Awareness Gate (CAG) architecture, a novel mechanism that dynamically adjusts the LLM’s input prompt based on whether the user query necessitates external context retrieval. Additionally, we introduce the Vector Candidates method, a core mathematical component of CAG that is statistical, LLM-independent, and highly scalable. We further examine the distributions of relationships between contexts and questions, presenting a statistical analysis of these distributions. This analysis can be leveraged to enhance the con- text retrieval process in retrieval-augmented generation (RAG) systems.
Papers List
List of archived papers
Similarity Measures in Medical Image Registration: A Review Article
Zohre Mohammadi - Dr Mohammad Reza Keyvanpour
Task Scheduling for Real-time Object Detection: Methods and Performance Comparison in ADAS Applications
Mahdi Seyfipoor - Sayyed Muhammad Jaffry - Siamak Mohamadi
SPA Bot: Smart Price-Action Trading Bot for Cryptocurency Market
Dr Hamid Jazayeriy - Mohammad Daryani
Securing the Internet of Things via Blockchain-Aided Smart Contracts
S. Mohammadali Zanjani - Hossein Shahinzadeh - Jalal Moradi - Zohreh Rezaei - Bahareh Kaviani-Baghbaderani - Sudeep Tanwar
Advanced SMS Spam Detection using Deep Complex Models and Sine-Cosine Algorithm
Sepehr Rezaei - Mohammadreza Shams - Mohsen Alambardar Meybodi
Statistical distance-base acceptance strategy for desirable offers in bilateral automated negotiation
Arash Ebrahimnezhad - Dr Hamid Jazayeriy - Dr Faria Nassiri-mofakham
Improving Drug-Target Interaction Prediction Using Enhanced Feature Selection
Maryam Taheri - Mohammad Reza Keyvanpour - Mohadeseh Saadat Mousavi
Customer Churn Prediction Using Data Mining Techniques for an Iranian Payment Application
Olya Rezaeian - Dr ُSeyedhamidreza Shahabi Haghighi - Dr Jamal Shahrabi
تشخیص حمله تزریق داده کاذب با روش OCD در شبکه هوشمند برق
محدثه جلیلی سنجرانی - سعید جلیلی - محمدکاظم شیخ الاسلامی
خوشه بندی ویسیلاب های دو آوایی زبان فارسی در کاربرد لب خوانی
مهسا هدایتی پور - دکتر یاسر شکفته - دکتر محسن ابراهیمی مقدم
more
Samin Hamayesh - Version 41.3.1