Abstract
This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs). These models, based on foundation models such as Large Language Models (LLMs) - trained on broad data - are tailored to address the demands of physics research. LPMs can function independently or as part of an integrated framework. This framework can incorporate specialized tools, including symbolic reasoning modules for mathematical manipulations, frameworks to analyse specific experimental and simulated data, and mechanisms for synthesizing theories and scientific literature. We begin by examining whether the physics community should actively develop and refine dedicated models, rather than relying solely on commercial LLMs. We then outline how LPMs can be realized through interdisciplinary collaboration among experts in physics, computer science, and philosophy of science. To integrate these models effectively, we identify three key pillars: Development, Evaluation, and Philosophical Reflection. Development focuses on constructing models capable of processing physics texts, mathematical formulations, and diverse physical data. Evaluation assesses accuracy and reliability by testing and benchmarking. Finally, Philosophical Reflection encompasses the analysis of broader implications of LLMs in physics, including their potential to generate new scientific understanding and what novel collaboration dynamics might arise in research. Inspired by the organizational structure of experimental collaborations in particle physics, we propose a similarly interdisciplinary and collaborative approach to building and refining Large Physics Models. This roadmap provides specific objectives, defines pathways to achieve them, and identifies challenges that must be addressed to realise physics-specific large scale AI models.
Abstract (translated)
本文探讨了一些理念,并为物理专用大规模人工智能模型的开发和评估提供了一条潜在的发展路线,我们将这些模型称为大型物理模型(LPMs)。这些基于广泛数据训练的基础模型(如大型语言模型LLMs)构建的模型,被专门设计来满足物理学研究的需求。LPMs 可以独立运作或作为综合框架的一部分运行。该框架可以整合专业的工具,包括用于数学操作的符号推理模块、分析特定实验和模拟数据的框架以及合成理论与科学文献的方法。 本文首先探讨了物理界是否应该积极开发和完善专用模型,而不仅仅是依赖商业化的LLMs。接着,我们概述了通过物理学、计算机科学和科学哲学专家之间的跨学科合作来实现LPMs的方式。为了有效地整合这些模型,我们确定了三个关键支柱:发展、评估以及反思。 - 发展专注于构建能够处理物理文本、数学表达式及多样化物理数据的模型。 - 评估则通过对模型进行测试与基准测试来衡量其准确性和可靠性。 - 反思涵盖了LLMs在物理学中的更广泛影响分析,包括它们可能产生的新科学理解以及研究中可能出现的新合作模式。 受粒子物理学实验协作组织结构的启发,我们提出了一种类似地跨学科且合作的方法来构建和改进大型物理模型。该路线图提供了具体的实现目标、达成这些目标的途径,并确定了必须解决以实现专门针对物理学的大规模AI模型所面临的挑战。
URL
https://arxiv.org/abs/2501.05382