0% Complete
English
صفحه اصلی
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Context Awareness Gate for Retrieval Augmented Generation
نویسندگان :
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
کلمات کلیدی :
Retrieval-Augmented Generation،Hallucination،Large Language Models،Open Domain Question Answering
چکیده :
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.
لیست مقالات
لیست مقالات بایگانی شده
LLM-Driven Feature Extraction for Stock Market Prediction: A case study of Tehran Stock Exchange
Siavash Hosseinpour Saffarian - Saman Haratizadeh
Improving Long-Term Engagement of Insurance Brokerages by Providing Gamified Configurations Based on The Delphi Method
Hosein Bayati - Fattaneh Taghiyareh - Sahand Hashemi
SBST challenges from the perspective of the test techniques
Sepideh Kashefi Gargari - Dr Mohammad Reza Keyvanpour
Classification of Personality Traits on Facebook Using Key Phrase Extraction, Language Models and Machine Learning
Faezeh Safari - Abdolah Chalechale
A perceptual loss for screen content image super-resolution
Hossein Sekhavaty-Moghadam - Marzieh Hosseinkhani - Dr Azadeh Mansouri
PeCoQ: A Dataset for Persian Complex Question Answering over Knowledge Graph
Romina Etezadi - Mehrnoush Shamsfard
Exploring the Relationship Between Gameplay Log Data and Depression & Anxiety
Soroush Elyasi - Arya Varasteh Nezhad - Fattaneh Taghiyareh
A Nano-based High-Speed QCA circuit for Information Security with Image Masking
Saeid Seyedi - Hatam Abdoli
پیش بینی ارتباط میزان مرگ و میر با هم زمانی وجود دو بیماری در مبتلایان به کرونا به کمک بگارگیری شبکه عصبی Word2Vec
سمن مثقالی - دکتر جواد عسکری سمن مثقالی - جواد عسکری -
Aspect-Based Sentiment Analysis of After-Sales Service Quality: A Case Study of Snowa and Competitors Using Digikala Reviews
Safiyeh Samadanian - Marjan Kaedi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.3