arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.25015cs.CLcs.AIcs.SE
收藏

命令干扰:社会语体影响大语言模型中的指令拓扑

Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models

the University of British Columbia(不列颠哥伦比亚大学);the Georgia Institute of Technology(佐治亚理工学院)

Tony Mason

AI总结:

研究探讨了社会语体如何影响大语言模型中指令拓扑,通过多语言实验发现指令拓扑反转由社会语体调解,改写指令可减少跨语言差异。

摘要:

系统提示指令在英语中协作,在西班牙语中竞争,语义相同但交互拓扑相反。本文通过四种语言和四种模型的指令级消融实验表明,拓扑反转由社会语体调解:命令语气在不同社群中具有不同强制力,多语言训练模型已学习这些惯例。单指令块的声明性改写可减少81%的跨语言差异(p=0.029,置换检验)。改写三个指令块使西班牙语指令拓扑从竞争转为协作,并影响未改写的块。这些发现表明模型将指令视为社会行为而非技术规范:'NEVER做X'是行使权威的命令,其强制力依赖语言,而'X:禁用'是事实描述,可跨语言转移。若语体在推理时调解指令遵循,可能在训练时也如此。本文提出可检验的预测:以命令语气撰写的宪法AI原则可能产生语言依赖的对齐。语料:22个手工编写探针,针对分解为56个块的生产系统提示。

英文摘要:

System prompt instructions that cooperate in English compete in Spanish, with the same semantic content, but opposite interaction topology. We present instruction-level ablation experiments across four languages and four models showing that this topology inversion is mediated by social register: the imperative mood carries different obligatory force across speech communities, and models trained on multilingual data have learned these conventions. Declarative rewriting of a single instruction block reduces cross-linguistic variance by 81% (p = 0.029, permutation test). Rewriting three of eleven imperative blocks shifts Spanish instruction topology from competitive to cooperative, with spillover effects on unrewritten blocks. These findings suggest that models process instructions as social acts, not technical specifications: "NEVER do X" is an exercise of authority whose force is language-dependent, while "X: disabled" is a factual description that transfers across languages. If register mediates instruction-following at inference time, it plausibly does so during training. We state this as a testable prediction: constitutional AI principles authored in imperative mood may create language-dependent alignment. Corpus: 22 hand-authored probes against a production system prompt decomposed into 56 blocks.

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。

↑