arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.14979cs.LGcs.AI
收藏

MLCopilot:在解决机器学习任务中释放大型语言模型的能力

MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks

Microsoft Research(微软研究院);ShanghaiTech University(上海科技大学)

Lei Zhang, Yuge Zhang, Kan Ren, Dongsheng Li, Yuqing Yang

AI总结:

本文提出MLCopilot框架,利用大型语言模型解决机器学习任务,通过理解结构化输入和推理,弥合机器智能与人类知识的差距,为新任务生成高竞争力的解决方案。

摘要:

机器学习(ML)领域已获得广泛采用,导致将ML适应于特定场景的需求显著增加,然而这既昂贵又非易事。解决ML任务自动化的主流方法(例如AutoML)通常耗时且对人类开发者来说难以理解。相比之下,尽管人类工程师具有理解任务和推理解决方案的惊人能力,但他们的经验和知识往往稀疏且难以通过定量方法加以利用。在本文中,我们旨在通过引入一个新颖的框架来弥合机器智能与人类知识之间的差距,该框架利用最先进的大型语言模型为新颖任务开发ML解决方案。我们展示了将LLMs的能力扩展到理解结构化输入并执行彻底推理以解决新颖ML任务的可能性。我们发现,经过一些专门设计后,LLM可以(i)从现有的ML任务经验中观察,并(ii)有效推理以为新任务提供有希望的结果。生成的解决方案可以直接使用以实现高水平的竞争力。示例和代码可在https://github.com/microsoft/CoML获取。

英文摘要:

The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers. In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches. In this paper, we aim to bridge the gap between machine intelligence and human knowledge by introducing a novel framework, which leverages the state-of-the-art large language models to develop ML solutions for novel tasks. We showcase the possibility of extending the capability of LLMs to comprehend structured inputs and perform thorough reasoning for solving novel ML tasks. And we find that, after some dedicated design, the LLM can (i) observe from the existing experiences of ML tasks and (ii) reason effectively to deliver promising results for new tasks. The solution generated can be used directly to achieve high levels of competitiveness. Examples and code available at https://github.com/microsoft/CoML.

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。

↑