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.
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
Faculty of Computing, Harbin Institute of Technology(哈尔滨工业大学计算机学院);Nanjing University(南京大学);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)
From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
Fudan University(复旦大学);School of Computer Science, Fudan University(复旦大学计算机科学技术学院);School of Data Science, Fudan University(复旦大学数据科学学院);Fudan-Aishu Cognitive Intelligence Joint Research Center(复旦-爱数认知智能联合研究中心)
How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework
Department Artificial Intelligence in Biomedical Engineering (AIBE)(人工智能生物医学工程系);Department of Digital Humanities and Social Studies (DHSS)(数字人文与社会科学系);University of Birmingham(伯明翰大学);Chair of AI-supported Therapy Decisions(人工智能支持治疗决策教授职位);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Institute of AI for Health, Helmholtz Zentrum München(健康人工智能研究所,海德堡中心慕尼黑)
How Output Format Confounds Data Quality and Capability in Instruction Tuning
University of Chinese Academy of Sciences(中国科学院大学);Pusan National University(釜山国立大学);Shenzhen University of Advanced Technology(深圳先进技术大学);Monash University(莫纳什大学)
LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback
School of Computation, Information and Technology, TUM(慕尼黑工业大学计算、信息与技术学院);Center for Information and Language Processing, LMU Munich(慕尼黑大学信息与语言处理中心);Munich Center for Machine Learning(慕尼黑机器学习中心);Bosch Center for Artificial Intelligence(博世人工智能中心)