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

TL;DR

This paper investigates how large language models tend to erase cultural and linguistic markers from non-native English varieties during text generation, quantifying this phenomenon and exploring ways to mitigate it.

Contribution

It introduces the concept of 'Cultural Ghosting' and develops novel metrics to measure cultural marker erasure in LLM outputs, providing insights into model biases and preservation strategies.

Findings

Overall identity erasure rate of 10.26% across models

Semantic similarity remains high despite cultural marker erasure

Explicit prompts reduce cultural erasure by 29%

Abstract

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.