Voice Under Revision: Large Language Models and the Normalization of Personal Narrative

TL;DR

This study investigates how large language models rewrite personal narratives, revealing a consistent stylistic normalization that impacts linguistic features and narrative voice, with implications for digital humanities and authorship analysis.

Contribution

It provides a detailed analysis of how LLM rewriting systematically alters stylistic features and narrative voice in personal texts, highlighting the directional nature of these changes.

Findings

LLM rewriting reduces function words, contractions, and first-person pronouns.

Vocabulary diversity, word length, and punctuation increase after rewriting.

Rewritten texts become more polished and less personalized, affecting authorship and style analysis.

Abstract

This study examines how large language model rewriting alters the style and narrative texture of personal narratives. It analyzes 300 personal narratives rewritten by three frontier LLMs under three prompt conditions: generic improvement, rewrite-only, and voice-preserving revision. Change is measured across 13 linguistic markers drawn from computational stylistics, including function words, vocabulary diversity, word length, punctuation, contractions, first-person pronouns, and emotion words. Across models and prompt conditions, LLM rewriting produces a consistent pattern of stylistic normalization. Function words, contractions, and first-person pronouns decrease, while vocabulary diversity, word length, and punctuation elaboration increase. These shifts occur whether the prompt asks the model to "improve" the text or simply to "rewrite" it. Voice-preserving prompts reduce the magnitude of the changes but do not eliminate their direction. Stylometric analysis shows that rewritten texts converge in feature space and become harder to match back to their source texts. Additional narrative markers indicate a shift from embedded to distanced narration, and from explicit causal reasoning to compressed abstraction. The findings suggest that contemporary LLMs exert a directional pull toward a more polished, less situated register. This has consequences for digital humanities and computational text analysis, where features such as function words, pronouns, contractions, and punctuation often serve as evidence for style, voice, authorship, and corpus integrity. LLM revision should therefore be understood not merely as surface-level editing, but as a consequential form of textual mediation.