Large Language Models (LLMs) are increasingly used to ``professionalize'' workplace communication, often at the cost of linguistic identity. We introduce "Cultural Ghosting", the systematic erasure of linguistic markers unique to non-native English varieties during text processing. Through analysis of 22,350 LLM outputs generated from 1,490 culturally marked texts (Indian, Singaporean,& Nigerian English) processed by five models under three prompt conditions, we quantify this phenomenon using two novel metrics: Identity Erasure Rate (IER) & Semantic Preservation Score (SPS). Across all prompts, we find an overall IER of 10.26%, with model-level variation from 3.5% to 20.5% (5.9x range). Crucially, we identify a Semantic Preservation Paradox: models maintain high semantic similarity (mean SPS = 0.748) while systematically erasing cultural markers. Pragmatic markers (politeness conventions) are 1.9x more vulnerable than lexical markers (71.5% vs. 37.1% erasure). Our experiments demonstrate that explicit cultural-preservation prompts reduce erasure by 29% without sacrificing semantic quality.

翻译：大语言模型（LLMs）正日益被用于“专业化”职场沟通，但这往往以牺牲语言身份为代价。我们提出“文化幽灵化”这一概念，指在文本处理过程中对非母语英语变体特有语言标记的系统性消除。通过对五种模型在三种提示条件下处理1,490篇文化标记文本（印度、新加坡和尼日利亚英语）所产生的22,350个LLM输出进行分析，我们使用两个新颖指标——身份消除率（IER）和语义保持分数（SPS）——量化了这一现象。在所有提示条件下，我们测得总体IER为10.26%，模型层面的IER变异范围为3.5%至20.5%（相差5.9倍）。关键的是，我们发现了语义保持悖论：模型在保持高语义相似性（平均SPS = 0.748）的同时，系统性地消除了文化标记。语用标记（礼貌规范）的消除率是词汇标记的1.9倍（71.5% vs. 37.1%）。我们的实验表明，明确的文化保护提示可在不牺牲语义质量的前提下，将消除率降低29%。