arXiv (All)
open access
Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- In-Place Instruction Following in Diffusion Language Models#975216
- Language that Lost Its Soul: Reflections on Language and Communication in the Digital Era#693725
- The Role of Socially-Mediated Alignment in the Development of Second Language Grammar and Vocabulary: Comparing Face-to-Face and Synchronous Mobile-Mediated Communication#492325
- Instruction Tuning for Large Language Models: A Survey#479898
- Do filled pauses serve a …um… communicative function? A comparison of self-directed and social speech#685089
Record · ID 1247356
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive