Downloads: 1
Research Paper | Computer Science and Information Technology | Volume 15 Issue 7, July 2026 | Pages: 1325 - 1337 | India
Question-Answer System on Medical Domain with LLMS Using Various Fine-Tuning & Rag with MCP Methods
Abstract: Developing artificial intelligence capable of clinical language comprehension and reliable diagnostic reasoning has remained a core challenge in biomedical engineering. While Large Language Models (LLMs) demonstrate significant potential in general natural language processing tasks, their direct application in the medical domain is severely constrained by parametric hallucinations and data silos. This paper introduces an end-to-end, resource-efficient, multilingual speech-driven Question-Answering (QA) framework optimized for localized clinical support. To accommodate deployment on consumer-grade execution environments, we implement Parameter-Efficient Fine-Tuning (PEFT) using Low-Rank Adaptation (LoRA) and 4-bit Quantized LoRA (QLoRA) configurations across open-source 3B and 7B parameter architectures. Human preference alignment is enforced via a stateful Reinforcement Learning with Human Feedback (RLHF) loop applying Proximal Policy Optimization (PPO). Crucially, to mitigate the vulnerabilities of passive information retrieval, we introduce an Active Validation Loop powered by Corrective Retrieval-Augmented Generation (CRAG). This validation engine is decoupled from the model harness using the Model Context Protocol (MCP), standardizing asyn-chronous lookups across dense vector repositories, clinical guidelines, and real-time electronic health registries. Evaluated on the MedMCQA and USMLE MedQA datasets, our integrated framework drastically reduces clinical hallucination rates by up to 58.1% while elevating baseline diagnostic accuracy from 45.0% to 68.4%. The resulting pipeline demonstrates a scalable, low-cost, and context-grounded AI paradigm suitable for edge-device clinical decision support systems.
Keywords: Medical, LLMS, Finetuning, Clinical decision support, Medical question answering, Clinical language models, Retrieval augmented generation, Low rank adaptation
How to Cite?: Misha Patel, "Question-Answer System on Medical Domain with LLMS Using Various Fine-Tuning & Rag with MCP Methods", Volume 15 Issue 7, July 2026, International Journal of Science and Research (IJSR), Pages: 1325-1337, https://www.ijsr.net/getabstract.php?paperid=SR26715120358, DOI: https://dx.doi.org/10.21275/SR26715120358