Jul 2026· 2026 7th International Conference on Smart Systems and Inventive Technology (ICSSIT)· pp. 1836-1841· 0 citations· 15 references
Abstract
Universities now use Large Language Models (LLMs) to transform their processes for managing student information. The paper introduces an upgraded chatbot system for Narasaraopeta Engineering College (NEC) which extends previous on-premise LLM chatbot research by providing four new functions. The system uses (1) Retrieval-Augmented Generation (RAG) to create citation-based responses through LlamaIndex and ChromaDB, (2) Context Memory which maintains conversation flow during multiple dialogue exchanges, (3) Voice Input through OpenAI Whisper Speech-to-Text (STT) technology, and (4) Multilingual Support which covers English and these seven languages: Hindi, Telugu, Tamil, Kannada, and Malayalam through IndicNLP. The system tested 60 benchmark questions across four academic categories which included regulations and examination policies and fee structures and multilingual queries and achieved 96.7% overall accuracy with sub-second text response times and 1.0–1.4 second voice response times. The system operates entirely on-premise through Docker which safeguards institutional data privacy while eliminating the need for recurring cloud API expenses. The upcoming development will create Emotion-Aware AI, FAQ Auto-Learning, Student Portal Integration, and a Mobile Application.
It is concluded that an NLP- and RAG-based chatbot is feasible to be implemented as a digital campus information service and improves answer accuracy from 58.5% to 89.25%, with an average response time below three seconds.
Zuhri Yanda, Yeni Yanti, Maulinda et al.· IC-ITECHS· 0 citations
Results suggest that code-mixing-aware RAG chatbots can meaningfully improve DSA learning outcomes while remaining feasible for instructor-led deployment in low-resource settings.
Saroj Bhandari, Puja Dhital· Aadim Journal of Multidiscip...· 0 citations
The results show that the RAG architecture provides a scalable alternative for creating precise, contextually grounded conversational agents, thereby mitigating some of the main drawbacks of LLMs.
Rabia Shabbir, K. Talpur, Shakeel Ahmad· ICCK Transactions on Machine...· 0 citations
A strong student support system plays a crucial role in providing
quality education for students. Facilitating the requisite support to students in the academic environment by human facilitators is still an uphill task, as facilitators are inherently subject to
changes in knowledge levels and emotional states, which can affect the quality of service expected.
In this research article, the authors have designed a retrieval-based multimodal and
multilingual chatbot interface using artificial intelligence and machine learning algorithms.
The authors have considered both continuous speech and text inputs to interact with the chatbot
in the domain of educational institutions. The chatbot can be interacted with by the students in
three languages, namely Hindi, Odia, and English.
The authors have rigorously validated the proposed artificial intelligence and machine
learning-driven chatbot models using various statistical metrics, including F1 score, Precision,
Recall, Sensitivity, Specificity, Confusion matrix, BLEU score, Wilcoxon signed-rank test, and
95% Confidence Intervals (CI), etc. Our proposed DNN-based model has yielded promising
results compared to other algorithms, including SVM, Naïve Bayes, KNN, Random Forest, and
Gradient Boost. BLEU scores for a multimodal, multilingual chatbot in Hindi, Odia, and English are 0.89, 0.92, and 0.91, respectively.
Our proposed architecture for the MM-chatbot can accept queries in both voice
and text modes. A pronunciation dictionary has been integrated to address pronunciation variations, accents, and speaking styles among stakeholders. MM-chatbot can generate voice responses in accordance with the user’s query language. We have significantly improved the
voice output of our proposed MM-chatbot by manipulating pitch in the synthesized speech.
However, users are required to explicitly select the query language at the beginning of their
conversation with the MM-chatbot.
This research aims to design a multimodal and multilingual chatbot that can be
useful for retrieving information from student support systems in educational institutions. Further the authors have proposed a chatbot that can operate in both voice and text modes.
Basanta Kumar Swain, G. Behera, A. Bhoi· Recent Advances in Computer...· 0 citations
This paper presents the design and implementation of intelligent chatbots using Retrieval-Augmented Generation architecture to derive accurate, context-based responses from domain-specific knowledge sources such as PDFs and CSV files. The proposed system integrates information retrieval mechanisms with large language models to overcome crucial limitations of traditional chatbots: hallucination, knowledge cut-off, and inability to access private organizational data. The proposed architecture uses a six-stage pipeline consisting of document ingestion, text splitting, and embedding generation with sentence transformers, semantic retrieval, and response generation via Large Language Models (LLMs). By preprocessing the PDF and CSV documents using a RecursiveCharacterTextSplitter and converting them into 384-dimensional semantic embeddings, the system works via a similarity-based retrieval of document chunks. For implementation, the LlamaIndex framework was used for data indexing and query orchestration, and HuggingFace Transformers for language modeling. Experimental validation conducted on the smart campus chatbot system demonstrated significant improvements in the accuracy, relevance and transparency of responses across education, student services, and administrative support domains compared with a standalone language model. Because of its modular design, it supports a wide range of domain-specific topics without the combinatorial costs of re-training. This is another important application for systems that require regular updates and accurate information. Overall, the proposed framework provides a simple and practical approach for easily implementing domain-aware chatbots.
Varsha Spoorthi Shree Narravula, V. K, Yashaswini B. Suresh et al.· 2026 7th International Confe...· 0 citations
A Retrieval-Augmented Generation (RAG)-based chatbot for academic regulation information services using a locally deployed Large Language Model (LLM) and promising feasibility for supporting document-based academic regulation information services is indicated.
