concept

medical question answering

Also known as: medical question answering system, medical question answering systems

Facts (15)

Sources

Medical Hallucination in Foundation Models and Their ... medrxiv.org medRxiv Mar 3, 2025 5 facts

claimFine-tuned LLaMA family models demonstrate capability in medical question-answering and cross-language adaptability.

procedureThe interactive self-reflection methodology (Ji et al., 2023) for medical question answering systems proceeds in two steps: (1) initiate with a knowledge acquisition prompt to generate relevant biomedical concepts for a patient presentation, and (2) perform iterative fact-checking queries to verify consistency between generated concepts and current medical guidelines.

referencePMC-LLaMA is a medical-purpose LLM fine-tuned from LLaMA on PubMed Central, a free archive of biomedical and life sciences literature, to enhance performance in medical question answering and knowledge retrieval.

referenceMedRAG is a systematic toolkit designed for medical question answering that combines multiple medical datasets with diverse retrieval techniques to improve LLM performance in clinical tasks, as described by Xiong et al. (2024b).

claimLarge Language Models (LLMs) used in Medical Question Answering and Clinical Documentation Automation require accurate descriptions of medical imaging or laboratory results.

Bridging the Gap Between LLMs and Evolving Medical Knowledge arxiv.org arXiv Jun 29, 2025 4 facts

referenceKaran Singhal et al. (2025) published 'Toward expert-level medical question answering with large language models' in Nature Medicine, pages 1–8, focusing on medical question answering capabilities of large language models.

claimThe Agentic Medical Graph-RAG (AMG-RAG) framework automates the construction and continuous updating of Medical Knowledge Graphs (MKGs) and integrates reasoning to retrieve external evidence for medical question answering.

claimLarge Language Models face two persistent challenges in medical question answering: maintaining factual currency in a field where knowledge becomes obsolete rapidly, and correctly modeling intricate relationships among medical entities.

claimAMG-RAG utilizes tools such as PubMedSearch and WikiSearch to dynamically integrate domain-specific knowledge, which improves its ability to answer medical questions.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 2 facts

referenceGuo, Cao, and Yi (2022) created a medical question answering system that utilizes both large language models and knowledge graphs.

claimIn the medical domain, integrating knowledge graphs with large language models improves medical question answering by providing more accurate and contextually relevant answers to complex queries, as demonstrated by systems like MEG and LLM-KGMQA.

A Comprehensive Benchmark and Evaluation Framework for Multi ... arxiv.org arXiv Jan 6, 2026 2 facts

referenceLLM-MedQA is a framework for enhancing medical question answering in Large Language Models through the use of case studies, as described by Yang et al. in January 2025.

referenceSinghal et al. (2023) explored methods for achieving expert-level medical question answering using Large Language Models in their paper 'Towards Expert-Level Medical Question Answering with Large Language Models'.

Reference Hallucination Score for Medical Artificial ... medinform.jmir.org JMIR Medical Informatics Jul 31, 2024 1 fact

referenceYang et al. (2025) conducted a design and evaluation study on using large language model synergy for ensemble learning in medical question answering, published in the Journal of Medical Internet Research.

LLM-KG4QA: Large Language Models and Knowledge Graphs for ... github.com GitHub 1 fact

referenceThe paper titled 'Trustworthy Medical Question Answering: An Evaluation-Centric Survey' was published on arXiv in 2025.