返回全部动态
隐喻诱导的算法引导：LLM代码生成中的跨领域程序迁移
原标题：Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation
AI 摘要
该研究探讨了大型语言模型在代码生成中受隐喻指令影响的现象，发现隐喻可能引发跨领域程序性迁移，导致模型生成低效算法。研究者开发了MASC框架来诱发和检测这种“隐喻算法引导”效应，并通过行为评估和表征分析验证了其机制。结果表明，隐喻技能通过转移源领域的程序模式而非表面语言影响模型输出。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Computer Science > Software Engineering Title:Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation View PDF HTML (experimental) Abstract:Large language models benefit from elements in natural language, such as metaphors and analogies in training data and inference input to achieve generalisability across different domains. However, these language elements may also lead to unwanted behaviors when metaphorical expressions implicitly transfer in
发布时间：2026-08-03 12:00
抓取时间：2026-08-03 19:22
来源机构：arXiv