VidyaRANG: Conversational Learning Based Platform powered by Large Language Model

• URL: http://arxiv.org/abs/2407.16209v1
• Date: Tue, 23 Jul 2024 06:30:35 GMT
• Title: VidyaRANG: Conversational Learning Based Platform powered by Large Language Model
• Abstract summary: Large Language Models fail to provide answers to questions derived from sensitive confidential information. This is where knowledge-augmented retrieval techniques become particularly useful. The proposed platform is designed to cater to the needs of learners from divergent fields.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Providing authoritative information tailored to a student's specific doubt is a hurdle in this era where search engines return an overwhelming number of article links. Large Language Models such as GPTs fail to provide answers to questions that were derived from sensitive confidential information. This information which is specific to some organisations is not available to LLMs due to privacy constraints. This is where knowledge-augmented retrieval techniques become particularly useful. The proposed platform is designed to cater to the needs of learners from divergent fields. Today, the most common format of learning is video and books, which our proposed platform allows learners to interact and ask questions. This increases learners' focus time exponentially by restricting access to pertinent content and, at the same time allowing personalized access and freedom to gain in-depth knowledge. Instructor's roles and responsibilities are significantly simplified allowing them to train a larger audience. To preserve privacy, instructors can grant course access to specific individuals, enabling personalized conversation on the provided content. This work includes an extensive spectrum of software development and product management skills, which also circumscribe knowledge of cloud computing for running Large Language Models and maintaining the application. For Frontend development, which is responsible for user interaction and user experience, Streamlit and React framework have been utilized. To improve security and privacy, the server is routed to a domain with an SSL certificate, and all the API key/s are stored securely on an AWS EC2 instance, to enhance user experience, web connectivity to an Android Studio-based mobile app has been established, and in-process to publish the app on play store, thus addressing all major software engineering disciplines

Related papers

• Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education [53.25191965774678]
  We propose a framework exploiting cross-device federated learning to address different manifestations of behavioral and cognitive disengagement during remote learning.<n>We fit video-based cognitive disengagement detection models using facial expressions and gaze features.<n>Our results show great promise for privacy-preserving educational technologies promoting learner engagement.
  arXiv  Detail & Related papers  (2026-02-10T15:40:01Z)
• DISCO: A Browser-Based Privacy-Preserving Framework for Distributed Collaborative Learning [25.901830399728343]
  Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints.<n>This not only fragments the statistical power of predictive models, but creates an accessibility bias, where accuracy becomes inequitably distributed to those who have the resources to overcome these concerns.<n>We present DISCO: an open-source DIStributed COllaborative learning platform accessible to non-technical users, offering a means to collaboratively build machine learning models without sharing any original data or requiring any programming knowledge.
  arXiv  Detail & Related papers  (2025-11-24T22:16:07Z)
• KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server [48.04903443425111]
  Large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. Existing solutions, such as utilizing synthetic data for substitution, struggle to simultaneously improve performance and preserve privacy. We propose KnowledgeSG, a novel client-server framework which enhances synthetic data quality and improves model performance while ensuring privacy.
  arXiv  Detail & Related papers  (2024-10-08T06:42:28Z)
• Swarm Learning: A Survey of Concepts, Applications, and Trends [3.55026004901472]
  Deep learning models have raised privacy and security concerns due to their reliance on large datasets on central servers. Federated learning (FL) has introduced a novel approach to building a versatile, large-scale machine learning framework. Swarm learning (SL) has been proposed in collaboration with Hewlett Packard Enterprise (HPE) SL represents a decentralized machine learning framework that leverages blockchain technology for secure, scalable, and private data management.
  arXiv  Detail & Related papers  (2024-05-01T14:59:24Z)
• Integrating A.I. in Higher Education: Protocol for a Pilot Study with 'SAMCares: An Adaptive Learning Hub' [0.6990493129893112]
  This research aims to introduce an innovative study buddy we will be calling the 'SAMCares' The system leverages a Large Language Model (LLM) and Retriever-Augmented Generation (RAG) to offer real-time, context-aware, and adaptive educational support.
  arXiv  Detail & Related papers  (2024-05-01T05:39:07Z)
• Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion [16.563311988191636]
  We construct an entity-centric knowledge store for each user based on their search and browsing activities on the web. This knowledge store is light-weight, since it only produces user-specific aggregate projections of interests and knowledge onto public knowledge graphs.
  arXiv  Detail & Related papers  (2023-11-10T01:18:47Z)
• KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases [55.942342665806656]
  KnowledGPT is a comprehensive framework to bridge large language models with various knowledge bases. The retrieval process employs the program of thought prompting, which generates search language for KBs in code format. KnowledGPT offers the capability to store knowledge in a personalized KB, catering to individual user demands.
  arXiv  Detail & Related papers  (2023-08-17T13:07:00Z)
• The Web Can Be Your Oyster for Improving Large Language Models [98.72358969495835]
  Large language models (LLMs) encode a large amount of world knowledge. We consider augmenting LLMs with the large-scale web using search engine. We present a web-augmented LLM UNIWEB, which is trained over 16 knowledge-intensive tasks in a unified text-to-text format.
  arXiv  Detail & Related papers  (2023-05-18T14:20:32Z)
• Augmented Large Language Models with Parametric Knowledge Guiding [72.71468058502228]
  Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. Their performance may be suboptimal for domain-specific tasks that require specialized knowledge due to limited exposure to the related data. We propose the novel Parametric Knowledge Guiding (PKG) framework, which equips LLMs with a knowledge-guiding module to access relevant knowledge.
  arXiv  Detail & Related papers  (2023-05-08T15:05:16Z)
• FedBot: Enhancing Privacy in Chatbots with Federated Learning [0.0]
  Federated Learning (FL) aims to protect data privacy through distributed learning methods that keep the data in its location. The POC combines Deep Bidirectional Transformer models and federated learning algorithms to protect customer data privacy during collaborative model training. The system is specifically designed to improve its performance and accuracy over time by leveraging its ability to learn from previous interactions.
  arXiv  Detail & Related papers  (2023-04-04T23:13:52Z)
• TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations [49.20701800683092]
  We present TIPRDC, a task-independent privacy-respecting data crowdsourcing framework with anonymized intermediate representation. The goal of this framework is to learn a feature extractor that can hide the privacy information from the intermediate representations; while maximally retaining the original information embedded in the raw data for the data collector to accomplish unknown learning tasks.
  arXiv  Detail & Related papers  (2020-05-23T06:21:26Z)
• An Overview of Privacy in Machine Learning [2.8935588665357077]
  This document provides background information on relevant concepts around machine learning and privacy. We discuss possible adversarial models and settings, cover a wide range of attacks that relate to private and/or sensitive information leakage.
  arXiv  Detail & Related papers  (2020-05-18T13:05:17Z)
• A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service [68.84245063902908]
  This paper introduces a novel distributed architecture for deep-learning-as-a-service. It is able to preserve the user sensitive data while providing Cloud-based machine and deep learning services.
  arXiv  Detail & Related papers  (2020-03-30T15:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.