Large language models in medicine

By Arun James Thirunavukarasu, Darren S. J. Ting, K. Elangovan, Laura Gutierrez, Ting Fang Tan, D. Ting. Nature Medicine, 2023

3,417 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Health Informatics

View Paper: https://www.semanticscholar.org/paper/94ce1d5924e05e8d75e43ce70044293ddcef850a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tijmen Blankevoort
2. Weidi Xie
3. Raghuraman Krishnamoorthi
4. Yan Tao
5. Yanfeng Wang
6. Zechun Liu
7. Changsheng Zhao
8. Vikas Chandra

In Health Informatics

1. Yan Tao
2. René F. Kizilcec
3. Ryan S. Baker
4. Olga Viberg

Citations in the corpus

• Jailbreaking Black Box Large Language Models in Twenty Queries (2023, neutral): “Although still at its infancy, the field of study surrounding large language models (LLMs) has shown significant promise in advancing numerous fields, including code generation [28], business analytics [38], and medicine [32].”
• Safe RLHF: Safe Reinforcement Learning from Human Feedback (2023, neutral): “Such unpredictability in behavior can be especially perilous in sensitive domains like medicine (Thirunavukarasu et al., 2023; Clusmann et al., 2023), where model-generated misinformation could have severe repercussions.”
• The rise and potential of large language model based agents: a survey (2025, neutral): “Professional domain knowledge refers to the knowledge associated with a specific domain like programming [124, 126, 127], mathematics [128], medicine [129], etc.”
• A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, neutral): “The study [29] argued that a primary concern relates to the potential perpetuation of”
• Cultural bias and cultural alignment of large language models (2023, background): “…Mistral, and LLaMA, which are trained on Internet-scale textual data to process text and produce human-sounding language, are increasingly used by people in all aspects of their life, including education [32], medicine and public health [13, 45], as well as creative and opinion writing [50, 29].”
• SpinQuant: LLM quantization with learned rotations (2024, methodology): “SoTA open source models ( e.g. , LLaMA [41], Mistral [17], etc) and proprietary LLMs ( e.g. , GPT [2], Gemini[38], etc) have been used in general purpose chatting assistants, medical diagnosticians [39], computer game content generators [10], coding co-pilots [34], and much more.”
• Large language models in healthcare and medical domain: A review (2023, background): “3 Large Language Models in Healthcare and Medical Domain Language models have become a revolutionary force in the constantly changing world of healthcare and medicine, revolutionising how medical researchers and practitioners engage with data, patients, and huge corpus of medical knowledge [36].”
• HealthBench: Evaluating Large Language Models Towards Improved Human Health (2025, neutral): “With the success of scaling language models, there has been increased interest in their application in healthcare (Clusmann et al., 2023; Thirunavukarasu et al., 2023; Lee et al., 2023; Liu et al., 2023; Moor et al., 2023; Singhal et al., 2023; Omiye et al., 2024; Zakka et al., 2024; Nori et al.,…”
• A generalist vision–language foundation model for diverse biomedical tasks (2023, neutral): “AI techniques, especially transformer-based foundation models, have demonstrated their power in solving a wide range of biomedical tasks, including radiology interpretation, clinical-information summarization and precise disease diagnostics 1 .”
• A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly (2023, background): “…not only provide technical support to domains directly related to language processing (e.g., search engines [340, 13], customer support [250], translation [316, 133]) but also find utility in more general scenarios such as code generation [113], healthcare [265], finance [299], and education [177].”
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering (2023, methodology): “Existing MedVQA methods [25, 22, 6, 20] typically treat the problem as a retrieval task with a limited answer base and train multi-modal vision-language models with contrastive or classification objectives.”