When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 29 references that are in the map. First posted on arXiv 25 Feb 2026.
Builds on
12 of 29 references.
References · 12
- 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttrainingcited by 117
- 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 59
- 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Editscited by 49
- 2021EmailSum: Abstractive Email Thread Summarizationcited by 24
- 2024Towards Trustworthy AI: A Review of Ethical and Robust Large Language Modelscited by 21
- 2025Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)cited by 19
- 2024Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Biascited by 14
- 2025Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMscited by 9
- 2025Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Modelscited by 8
- 2025Detecting Linguistic Indicators for Stereotype Assessment with Large Language Modelscited by 5
- 2025TRACE: Transparent Web Reliability Assessment with Contextual Explanationscited by 5
- 2025Invisible Languages of the LLM Universecited by 4
Built on by
Not cited yet.