语言不同，指令的互动方式也不同，模型把它当社会行为理解。
Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models
- 用社会语体差异解释指令拓扑变化，跨语言指令互动模式反转
- 改写单个指令块使跨语言差异降低81%，三个改写可改变西班牙语指令结构
- 适合关注提示工程、多语言对齐与模型社会认知的研究者
同一语义内容在英语中指令协作，在西班牙语中则竞争，交互拓扑相反。我们在四种语言和四种模型上进行指令级消融实验，发现这种拓扑反转由社会语体（social register）中介：祈使语气在不同语境中具有不同的强制力，而多语言训练模型已习得这些规范。将单一指令块改写为陈述句，可使跨语言差异减少81%（p = 0.029，置换检验）。改写十一组指令中的三组，即可将西班牙语指令拓扑从竞争转为协作，并产生未改写部分的扩散效应。结果表明，模型将指令视为社会行为而非技术说明：'绝不要做X'是权威表达，其效力依赖语言；而'禁用X'是事实描述，跨语言通用。若语体在推理时影响指令遵循，训练阶段也可能如此。我们提出可验证预测：以祈使语气撰写的宪法型AI原则可能引发语言依赖的对齐偏差。数据集：22个手工设计探针，针对生产系统提示，分解为56个指令块。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。