Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197077,
        author = {Nancy Jenifer A and Varssha B and Vishnupriya B},
        title = {Explainable and Verifiable Retrieval-Augmented Conversational Agent with Hallucination Control},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5876-5879},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197077},
        abstract = {This paper proposes a hallucination-free Retrieval-Augmented Generation (RAG) enabled chatbot designed to improve the accuracy and reliability of responses generated by large language models. Traditional language models often produce hallucinated or incorrect information due to their reliance on pre-trained knowledge. To address this issue, the proposed system integrates document retrieval with transformer-based language models using LangChain and embedding models from Hugging Face Transformers. The system retrieves relevant information from external documents using vector similarity search implemented through FAISS and generates responses using a local LLM executed via Ollama. Experimental evaluation using BLEU score and qualitative analysis demonstrates that the RAG-based chatbot significantly reduces hallucination and improves response accuracy compared to standard LLMs. The system is suitable for applications requiring reliable and domain-specific information retrieval.},
        keywords = {RAG, Hallucination, Chatbot, LangChain, Hugging Face, FAISS, Embeddings, LLM},
        month = {April},
        }