arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.02203cs.CLcs.AI
收藏

通过大型语言模型实现自动适应规则优化

Automatic Adaptation Rule Optimization via Large Language Models

School of Computing, Tokyo Institute of Technology(东京工业大学计算学院);Department of Computer Science and Engineering, Waseda University(早稻田大学计算机科学与工程学院);Graduate School of Information Science and Technology, University of Tokyo(东京大学信息科学与技术研究生院)

Yusei Ishimizu, Jialong Li, Jinglue Xu, Jinyu Cai, Hitoshi Iba, Kenji Tei

AI总结:

针对基于规则的自适应中规则设计搜索困难的问题,本文提出利用 LLM 的常识与推理能力作为优化器自动构建和优化适应规则,并在 SWIM 中初步验证了其效果与局限。

摘要:

基于规则的适应是自适应的一种基础方法,具有人类可读性和快速响应的特点。然而,构建高性能且鲁棒的适应规则通常是一项挑战,因为其本质上涉及在复杂的(变量)空间中搜索最优设计。为此,本文尝试利用大型语言模型(LLM)作为优化器来构建和优化适应规则,借助 LLM 内在的常识和推理能力。在 SWIM 中开展的初步实验验证了本方法的有效性与局限性。

英文摘要:

Rule-based adaptation is a foundational approach to self-adaptation, characterized by its human readability and rapid response. However, building high-performance and robust adaptation rules is often a challenge because it essentially involves searching the optimal design in a complex (variables) space. In response, this paper attempt to employ large language models (LLMs) as a optimizer to construct and optimize adaptation rules, leveraging the common sense and reasoning capabilities inherent in LLMs. Preliminary experiments conducted in SWIM have validated the effectiveness and limitation of our method.

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。

↑