A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing
Department of Computing;Games, Teesside University, Middlesbrough, United Kingdom Centre for Digital Innovation, Teesside University, Middlesbrough, United Kingdom Faculty of Business \& Technology, University of Sunderland, Sunderland, United Kingdom
Naeimeh Nourmohammadi, Md Meem Hossain, The Anh Han, Safina Showkat Ara, Zia Ush Shamszaman
Large language models (LLMs) show promise for healthcare question answering, but clinical use is limited by weak verification, insufficient evidence grounding, and unreliable confidence signalling. We propose a multi-agent medical QA framework that combines complementary LLMs with evidence retrieval, uncertainty estimation, and bias checks to improve answer reliability. Our approach has two phases. First, we fine-tune three representative LLM families (GPT, LLaMA, and DeepSeek R1) on MedQuAD-derived medical QA data (20k+ question-answer pairs across multiple NIH domains) and benchmark generation quality. DeepSeek R1 achieves the strongest scores (ROUGE-1 0.536 +- 0.04; ROUGE-2 0.226 +-0.03; BLEU 0.098 -+ 0.018) and substantially outperforms the specialised biomedical baseline BioGPT in zero-shot evaluation. Second, we implement a modular multi-agent pipeline in which a Clinical Reasoning agent (fine-tuned LLaMA) produces structured explanations, an Evidence Retrieval agent queries PubMed to ground responses in recent literature, and a Refinement agent (DeepSeek R1) improves clarity and factual consistency; an optional human validation path is triggered for high-risk or high-uncertainty cases. Safety mechanisms include Monte Carlo dropout and perplexity-based uncertainty scoring, plus lexical and sentiment-based bias detection supported by LIME/SHAP-based analyses. In evaluation, the full system achieves 87% accuracy with relevance around 0.80, and evidence augmentation reduces uncertainty (perplexity 4.13) compared to base responses, with mean end-to-end latency of 36.5 seconds under the reported configuration. Overall, the results indicate that agent specialisation and verification layers can mitigate key single-model limitations and provide a practical, extensible design for evidence-based and bias-aware medical AI.
A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1
Faculty of Computer Science, Electronics, and Telecommunications AGH University of Krakow(计算机科学、电子与电信学院AGH克拉科夫大学);Faculty of Humanities AGH University of Krakow(人文学院AGH克拉科夫大学);Institute of Mathematics University of Silesia(数学学院桑特学院)
A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2
Faculty of Computer Science, Faculty of Humanities(计算机科学系,人文科学系);Institute of Mathematics Faculty of Humanities(人文科学学院数学研究所);University of Silesia(斯蒂利亚大学);AGH University of Krakow(克拉科夫AGH大学)
Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models
Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院);University of Texas Health(德克萨斯大学健康科学中心);Virginia Hospital Center(弗吉尼亚医院中心);Shahid Beheshti University of Medical Sciences(沙希德·贝赫什提医科大学);Stanford University(斯坦福大学);Cedars-Sinai Medical Center(西达赛奈医疗中心);Inova Fairfax Medical Campus(伊诺瓦费尔法克斯医疗中心);University of California–Los Angeles(加州大学洛杉矶分校);NYU Grossman School of Medicine(纽约大学格罗斯曼医学院);Columbia University(哥伦比亚大学)
MGH Radiology Llama: A Llama 3 70B Model for Radiology
School of Computing, University of Georgia(佐治亚大学计算学院);Department of Radiology, Massachusetts General Hospital and Harvard Medical School(麻省总医院及哈佛医学院放射科)
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
School of Computer Science, Fudan University(复旦大学计算机科学学院);School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院);Institute of Modern Languages and Linguistics, Fudan University(复旦大学现代语言与语言学研究所);Institute of Trustworthy Embodied Artificial Intelligence, Fudan University(复旦大学可信具身人工智能研究所);Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心);Pengcheng Laboratory(鹏城实验室);Hikvision Inc(海康威视公司)
AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models
Centro de Investigación Científica y de Educación Superior de Ensenada(恩森亚达科学与高等教育研究中心);Facultad de Ciencias, UNAM(科学学院,国立自治大学);Facultad de Matemáticas, Universidad Veracruzana(数学学院,韦拉克鲁斯大学)
DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models
Weill Cornell Medicine, Cornell University(威尔康奈尔医学院,康奈尔大学);Johns Hopkins University(约翰斯·霍普金斯大学);Touro University College of Osteopathic Medicine(图罗大学整骨医学院)
HPC-GPT: Integrating Large Language Model for High-Performance Computing
University of California, Merced(加州大学默塞德分校);Argonne National Laboratory(阿贡国家实验室);Iowa State University(爱荷华州立大学);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);Binghamton University(宾汉姆顿大学)
GP-GPT: Large Language Model for Gene-Phenotype Mapping
Department of Computer Science and Engineering, The University of Texas at Arlington(计算机科学与工程系,德克萨斯理工大学 Arlington 分校);School of Computing, University of Georgia(计算学院,佐治亚大学);Department of Computer Science, Indiana University Indianapolis(计算机科学系,印第安纳大学 Indianapolis 分校);Department of Radiology, Massachusetts General Hospital and Harvard Medical School(放射科,麻省总医院和哈佛医学院);Department of Statistics, University of Georgia(统计系,佐治亚大学);Department of Epidemiology & Biostatistics, University of Georgia(流行病学与生物统计学系,佐治亚大学);Department of Environmental Health Science, University of Georgia(环境流行病学系,佐治亚大学)
Leveraging Fine-Tuned Large Language Models for Interpretable Pancreatic Cystic Lesion Feature Extraction and Risk Categorization
New York University(纽约大学);Columbia University Irving Medical Center(哥伦比亚大学欧文医学中心);NYU Grossman School of Medicine(纽约大学格罗斯曼医学院);University of California San Diego(加州大学圣地亚哥分校)
Is Open-Source There Yet? A Comparative Study on Commercial and Open-Source LLMs in Their Ability to Label Chest X-Ray Reports
Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院 Athinoula A. Martinos 生物医学成像中心);Charité - Universitätsmedizin Berlin(柏林夏里特医学院);Dana-Farber Cancer Institute(丹娜法伯癌症研究院)
Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development
Chalmers University of Technology;University of Gothenburg Gothenburg Sweden;Research \& Development, Volvo Car Corporation Gothenburg Sweden;University of Gothenburg;Research \& Development, Volvo Car Corporation