利用语言模型协同人类专业知识与AI效率,用于显微镜操作和自动化实验设计
Synergizing Human Expertise and AI Efficiency with Language Model for Microscopy Operation and Automated Experiment Design
AI总结:
本文评估ChatGPT4结合API辅助扫描探针显微镜实验设计、工作流编程与数据分析的能力,发现其擅长代码生成和基础图像分析但难以深入设计,指出领域微调LLM可促进人机协同。
摘要:
随着开源和专有领域大型语言模型(LLM)的出现,人们的注意力正转向如何利用这类人工智能(AI)系统辅助复杂的科学任务,例如材料合成、表征、分析和发现。本文中,我们探索了LLM(尤其是ChatGPT4)结合应用程序编程接口(API)在扫描探针显微镜的实验设计、编程工作流和数据分析任务中的效用,同时使用了内部开发的API和商业供应商提供的用于仪器控制的API。我们发现,LLM在将实验工作流的构想转换为显微镜API上的可执行代码方面尤其有用。除代码生成之外,我们发现GPT4能够在一般意义上分析显微镜图像。同时,我们发现GPT4存在局限,无法超越基础分析或开展更深入的技术性实验设计。我们认为,针对个别科学领域专门微调的LLM,有可能成为更好的语言接口,用于将人类专家的科学构想转换为可执行工作流;这种人类专业知识与LLM实验效率之间的协同,能够为加速科学研究打开新的大门,并在科学界实现有效的实验方案归档与共享。
英文摘要:
With the advent of large language models (LLMs), in both the open source and proprietary domains, attention is turning to how to exploit such artificial intelligence (AI) systems in assisting complex scientific tasks, such as material synthesis, characterization, analysis and discovery. Here, we explore the utility of LLM, particularly ChatGPT4, in combination with application program interfaces (APIs) in tasks of experimental design, programming workflows, and data analysis in scanning probe microscopy, using both in-house developed API and API given by a commercial vendor for instrument control. We find that the LLM can be especially useful in converting ideations of experimental workflows to executable code on microscope APIs. Beyond code generation, we find that the GPT4 is capable of analyzing microscopy images in a generic sense. At the same time, we find that GPT4 suffers from inability to extend beyond basic analyses or more in-depth technical experimental design. We argue that a LLM specifically fine-tuned for individual scientific domains can potentially be a better language interface for converting scientific ideations from human experts to executable workflows, such a synergy between human expertise and LLM efficiency in experimentation can open new door for accelerating scientific research, enabling effective experimental protocols archive and sharing in scientific community.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。