Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation
知识边界探测与需求引导干预:面向基于LLM的电力系统代码生成
机构 * Department of Engineering, University of Exeter(工程系,埃克塞特大学) ; Department of Computer Science, University of Exeter(计算机科学系,埃克塞特大学)
专题命中 代码生成 :code generation(title,abstract);分类 cs.SE、cs.CL
AI总结 针对LLM在电力系统代码生成中因API知识边界错误导致失败的问题,提出PowerCodeBench基准、L0-L3文档驱动探测和边界感知干预方法,显著提升模型准确率。
Comments 43 pages, 12 figures, includes supplementary material