对比生成式大模型与传统NLP在医学中的表现差异。
The Evolving Landscape of Generative Large Language Models and Traditional Natural Language Processing in Medicine
- 分析19,123篇医学文献，比较两类技术在不同任务的表现。
- 生成式大模型在开放式任务中更优，传统NLP在信息抽取上占优。
- 强调伦理规范对医疗应用中技术发展的关键作用。
自然语言处理（NLP）在医学领域已有长期应用，而生成式大语言模型（LLMs）近年来日益突出。然而，二者在不同医学任务中的差异仍缺乏深入研究。本研究分析了19,123项相关研究，发现生成式大模型在开放性任务中表现更优，而传统NLP在信息提取与分析类任务中占据主导地位。随着技术持续发展，确保其在医疗场景中的伦理使用至关重要，以充分释放其潜在价值。
原文摘要 · Abstract (English)
Natural language processing (NLP) has been traditionally applied to medicine, and generative large language models (LLMs) have become prominent recently. However, the differences between them across different medical tasks remain underexplored. We analyzed 19,123 studies, finding that generative LLMs demonstrate advantages in open-ended tasks, while traditional NLP dominates in information extraction and analysis tasks. As these technologies advance, ethical use of them is essential to ensure their potential in medical applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。