# When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models

arXiv: https://arxiv.org/abs/2602.22145 · HTML: https://mlsanity.com/paper/2602.22145/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining](https://mlsanity.com/paper/2505.07608/) (2025)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)
- [EmailSum: Abstractive Email Thread Summarization](https://mlsanity.com/paper/2107.14691/) (2021)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)
- [Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)](https://mlsanity.com/paper/2505.21091/) (2025)
- [Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias](https://mlsanity.com/paper/2406.00020/) (2024)
- [Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMs](https://mlsanity.com/paper/2505.05660/) (2025)
- [Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models](https://mlsanity.com/paper/2504.07787/) (2025)
- [Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models](https://mlsanity.com/paper/2502.19160/) (2025)
- [TRACE: Transparent Web Reliability Assessment with Contextual Explanations](https://mlsanity.com/paper/2506.12072/) (2025)
- [Invisible Languages of the LLM Universe](https://mlsanity.com/paper/2510.11557/) (2025)

## 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.