RAG-Based Medical Chatbot for Healthcare Queries

This study presents a Retrieval-Augmented Generation (RAG)-based medical chatbot that enhances healthcare query responses by effectively combining retrieval mechanisms with generative models. The system generates context-aware and factually grounded answers, thereby reducing the inaccuracies commonly observed in traditional chatbot approaches. Experimental results indicate improved response relevance, clarity, and consistency across a wide range of medical queries. By leveraging semantic search and vector-based retrieval techniques, the chatbot efficiently accesses external knowledge sources to enrich its responses. However, the overall performance remains dependent on the quality and timely updates of the underlying knowledge base. Despite this limitation, the proposed approach demonstrates a scalable, reliable, and practical solution for intelligent healthcare assistance systems[10].

[1] P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems (NeurIPS), 2020. [2] S. Ji et al., “Survey of Hallucination in Natural Language Generation,” ACM Computing Surveys, 2023. [3] T. Brown et al., “Language Models are Few-Shot Learners,” NeurIPS, 2020. [4] A. Vaswani et al., “Attention Is All You Need,” NeurIPS, 2017.   [5] S. Robertson and H. Zaragoza, “The Probabilistic Relevance Framework: BM25 and Beyond,” Foundations and Trends in Information Retrieval, 2009. [6]  A. Holzinger et al., “What Do We Need to Build Explainable AI Systems for the Medical Domain?” arXiv preprint, 2017.   [7] N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” EMNLP, 2019.   [8] V. Karpukhin et al., “Dense Passage Retrieval for Open-Domain Question Answering,” EMNLP, 2020.   [9] O. Khattab and M. Zaharia, “ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT,” SIGIR, 2020.   [10] K. Roberts et al., “Overview of the TREC 2019 Precision Medicine Track,” Text Retrieval Conference (TREC), 2019.   [11]  M. Topol, Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again, Basic Books, 2019.   [12] H. Singhal et al., “Large Language Models Encode Clinical Knowledge,” Nature, 2023.   [13] J. Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” NAACL-HLT, 2019.   [14] S. Miner et al., “Smartphone-Based Conversational Agents and Responses to Questions about Mental Health, Interpersonal Violence, and Physical Health,” JAMA Internal Medicine, 2016. [15] X. Liu et al., “Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in NLP,” ACM Computing Surveys, 2023.   [16] M. Thoppilan et al., “LaMDA: Language Models for Dialog Applications,” arXiv preprint, 2022.