Context-Aware Large Language Model for Customer Support Chatbots

DEVELOPMENT OF A RAG-BASED SCHOLARLY RESEARCH CHATBOT WITH FINE-TUNED DENSE RETRIEVAL

Results show that fine-tuning and integrating the BAAI/bge-large model significantly improves the chatbot's ability to retrieve relevant information, demonstrating a significant boost in retrieving the most relevant scholarly information for user queries.

Large Language Models Hallucinate and How Retrieval- Augmented Generation Mitigates It

Large Language Models (LLMs) can generate fluent and convincing responses, but fluency does not guarantee factual correctness. Hallucination occurs when a model produces information that is false, unsupported, or inconsistent with available evidence. This paper reviews why hallucinations arise andexamine Retrieval-Augmented Generation (RAG) as a practical mitigation strategy. The discussion focuses on prediction-based generation, missing or outdated knowledge, ambiguous queries, and the absence of automatic verification. RAG addresses these limitations by retrieving relevant information from an external knowledge source and supplying it to the generator as contextual evidence. The paper describes the major stages of a RAG pipeline, including document ingestion, chunking, embeddings, vector storage, retrieval, context augmentation, and answer generation. It also examines the conditions under which RAG can fail, including poor retrieval, incomplete knowledge bases, unreliable sources, weak ranking, and incorrect interpretation of retrieved context. Finally, the paper discusses evaluation dimensions such as context relevance, answer faithfulness, and answer relevance, and outlines applications of RAG in education, enterprise search, technical support, research assistance, and document question answering. The analysis concludes that RAG should be viewed as a grounding and evidence-access mechanism rather than a guarantee of hallucination-free generation

An On-Premise Multilingual Academic Chatbot using Retrieval-Augmented Generation and Context-Aware Memory for University Assistance

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.

Leveraging Language Models for Textual Retrieval in the TREC 2025 DRAGUN Track

An Optimization Framework for Retrieval Augmented Generation in Indonesian Educational Question Answering

A RAG optimization framework for Indonesian-language educational question answering using a Human-Computer Interaction learning corpus as a case study is developed and provides a procedure for selecting retrieval and generation settings for a given corpus.

Evaluating User Experience of a Retrieval-Augmented Generation-Based Customer Service Chatbot

— As digital services become increasingly widespread, online real-time customer support has become a key way for consumers to seek help. A good service experience can boost customer satisfaction and loyalty, particularly in the financial sector. However, traditional keyword-based chatbots often fail to capture users ’ intent, limiting the scenarios in which they can be used. This study introduces a system based on Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs), aiming to better understand user queries and provide more helpful responses. Through interviews and sentiment analysis, we explored user reactions and what influenced their emotional responses. Findings revealed that traditional bots often triggered frustration and confusion due to rigid responses and poor understanding. In contrast, the RAG-based system demonstrated stronger natural language handling and was perceived as more empathetic. Some users even reported feeling emotionally supported. However, slow response times and difficulty in handling complex queries remained challenges. Based on these insights, we suggest improving response speed, adding voice interaction, and enhancing response reliability to guide future development of intelligent customer support tools.