一种通用的语气？通过SAEs寻找和控制语言无关的非正式语气
A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs
AI总结：
研究通过SAEs探测Gemma-2-9B-IT模型内部表示，发现多语言模型能处理非正式语气为跨语言抽象概念，而非孤立语言记忆。
摘要：
尽管多语言语言模型能跨语言转移事实和语法知识，但其是否将文化特定的语用语气如俚语作为孤立语言记忆还是统一抽象概念尚不明确。我们通过稀疏自编码器（SAEs）在英语、希伯来语和俄语三种语言上探测Gemma-2-9B-IT模型的内部表示，发现非正式语气信号在语言特定特征中分布广泛，但存在一个小而稳健的跨语言核心。该核心形成几何上一致的「非正式语气子空间」，在模型深层结构中逐渐增强。关键在于这些共享表示不仅是相关性的：通过这些特征的激活引导，输出的正式程度在所有源语言中发生变化，并能零样本迁移到六个未见语言中。这些结果提供了首次机制证据，表明多语言LLM内部将非正式语气不仅视为表面层次的启发式方法，而是作为可移植的、语言无关的语用抽象。
英文摘要：
While multilingual language models successfully transfer factual and syntactic knowledge across languages, it remains unclear whether they process culture-specific pragmatic registers, such as slang, as isolated language-specific memorizations or as unified, abstract concepts. We study this by probing the internal representations of Gemma-2-9B-IT using Sparse Autoencoders (SAEs) across three typologically diverse source languages: English, Hebrew, and Russian. To definitively isolate pragmatic register processing from trivial lexical sensitivity, we introduce a novel dataset in which every target term is polysemous, appearing in both literal and informal contexts. We find that while much of the informal-register signal is distributed across language-specific features, a small but highly robust cross-linguistic core consistently emerges. This shared core forms a geometrically coherent ``informal register subspace'' that sharpens in the model's deeper layers. Crucially, these shared representations are not merely correlational: activation steering with these features causally shifts output formality across all source languages and transfers zero-shot to six unseen languages spanning diverse language families and scripts. Together, these results provide the first mechanistic evidence that multilingual LLMs internalize informal register not just as surface-level heuristics, but as a portable, language-agnostic pragmatic abstraction.
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。
