“In the full paper[1] read the examples of GPT-4's actual responses, e.g. Figs 3.1 and 7.1 and forward. Very, very impressive. [1] https://arxiv.org/pdf/2303.13375.pdf”
Capabilities of GPT-4 on Medical Challenge Problems
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation across various domains, including medicine. We present a comprehensive evaluation of GPT-4, a state-of-the-art LLM, on medical competency examinations and benchmark datasets. GPT-4 is a general-purpose model that is not specialized for medical problems through training or engineered to solve clinical tasks. Our analysis covers two sets of official practice materials for the USMLE, a three-step examination program used to assess clinical competency and grant licensure in the United States. We also evaluate performance on the MultiMedQA suite of benchmark datasets. Beyond measuring model performance, experiments were conducted to investigate the influence of test questions containing both text and images on model performance, probe for memorization of content during training, and study probability calibration, which is of critical importance in high-stakes applications like medicine. Our results show that GPT-4, without any specialized prompt crafting, exceeds the passing score on USMLE by over 20 points and outperforms earlier general-purpose models (GPT-3.5) as well as models specifically fine-tuned on medical knowledge (Med-PaLM, a prompt-tuned version of Flan-PaLM 540B). In addition, GPT-4 is significantly better calibrated than GPT-3.5, demonstrating a much-improved ability to predict the likelihood that its answers are correct. We also explore the behavior of the model qualitatively through a case study that shows the ability of GPT-4 to explain medical reasoning, personalize explanations to students, and interactively craft new counterfactual scenarios around a medical case. Implications of the findings are discussed for potential uses of GPT-4 in medical education, assessment, and clinical practice, with appropriate attention to challenges of accuracy and safety.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Fun Facts - Not all these models are instruct aligned - Cohere's suite is free for personal use - anthropic uses reinforcement learning from ai feedback for instruct alignment, removing humans from the process almost entirely(humans still make the rules the language model checks the responses against). - open ai's models are pretty poorly calibrated c…”
“Base GPT-4 was highly calibrated. read open ai's technical paper. also, this paper on gpt-4 performance of medical challenge problems confirmed the high calibration for medicine https://arxiv.org/abs/2303.13375”
- Capabilities of GPT-4 on Medical Challenge Problems ↗georgehill · 2023-03-24 · 1 分
- Capabilities of GPT-4 on Medical Challenge Problems ↗bumbledraven · 2023-03-26 · 2 分