Large language models (LLMs) exhibit a vulnerability arising from being trained to be helpful: a tendency to comply with illogical requests that would generate false information, even when they have the knowledge to identify…
Continue Reading
We evaluated the ability of three leading LLMs (GPT-4o, Gemini 2.0 Experimental, and Claude 3.5 Sonnet) to recognize human facial expression using the NimStim dataset. GPT and Gemini matched or exceeded human performance, especially…
Continue Reading
Recent advances in artificial intelligence, particularly large language models (LLMs), show promise for mental health applications, including the automated detection of depressive symptoms from natural language. We fine-tuned a German BERT-based LLM to predict…
Continue Reading
While large language models (LLMs) hold promise for transforming clinical healthcare, current comparisons and benchmark evaluations of large language models in medicine often fail to capture real-world efficacy. Specifically, we highlight how key discrepancies…
Continue Reading
Generative AI models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used to interpret medical images and answer clinical questions. However, their responses often include inaccuracies; therefore, safety measures like medical…
Continue Reading
Generative artificial intelligence is revolutionizing digital twin development, enabling virtual patient representations that predict health trajectories, with large language models (LLMs) showcasing untapped clinical forecasting potential. We developed the Digital Twin—Generative Pretrained Transformer (DT-GPT),…
Continue Reading
Patients with diabetes are at increased risk of comorbid depression or anxiety, complicating their management. This study evaluated the performance of large language models (LLMs) in detecting these symptoms from secure patient messages. We…
Continue Reading
Electronic health records (EHRs) contain rich longitudinal information for clinical decision-making, yet LLMs struggle to reason across patient timelines. We introduce TIMER (Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records), a method to…
Continue Reading
“Using data sets of attacker-generated commands and responses, these models are trained to mimic server behaviors convincingly. Techniques such as supervised fine-tuning, prompt engineering and low-rank adaptations help tailor these models for specific tasks,”…
Continue Reading
With a growing shortage of clinicians and an aging population, more patients are seeking self-care information. But navigating the available AI tools remains a challenge even for the most internet savvy.
By John Halamka, M.D., Diercks…
Continue Reading
