当AI写作时，谁的声音仍保留？量化世界英语变体中大型语言模型的文化标记消失
When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models
AI总结：
研究揭示大型语言模型在处理不同英语变体时对文化标记的系统性消除现象，并提出量化指标与改进方法。
摘要：
大型语言模型（LLMs）越来越多地被用来“专业化学术”职场沟通，往往以牺牲语言身份为代价。我们引入了“文化幽灵”，即在文本处理过程中系统性地消除非母语英语变体特有的语言标记。通过分析22,350个由五个模型在三种提示条件下生成的LLM输出，这些输出源自1,490个具有文化标记的文本（印度英语、新加坡英语和尼日利亚英语），我们使用两个新的指标：身份消除率（IER）和语义保存分数（SPS）来量化这一现象。在所有提示条件下，我们发现总体身份消除率为10.26%，模型层面的差异从3.5%到20.5%（5.9倍范围）。关键的是，我们识别出一个语义保存悖论：模型保持高语义相似性（平均SPS=0.748）的同时，系统性地消除文化标记。语用标记（礼貌惯例）比词汇标记（71.5% vs. 37.1%消除）更易受攻击。我们的实验表明，显式的文化保存提示可将消除率降低29%，而不会牺牲语义质量。
英文摘要：
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.
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。
