The Rephrased Reality: Analysing Sentiment Shifts in LLM-Rephrased Text
Frederico Leite Richardson, Aline Villavicencio, Ronaldo Parente de Menezes · 2025
As Large Language Models (LLMs) become increasingly integrated into digital communication, their impact on the sentiment of text has become a critical area of investigation. This study explores the effects of iterative rephrasing by LLMs, particularly focusing on how repeated processing with neutral prompts influences sentiment expression. Our research identifies distinct patterns of sentiment drift, revealing that open-source LLMs tend to shift towards a positive sentiment over multiple iterations, which may lead to a homogenization of emotional expression in digital discourse. In contrast, advanced models such as GPT-4o demonstrate a superior ability to preserve the original sentiment across iterations. To quantify these effects, we introduce the Sentiment Fidelity Score, a novel metric that assesses the capacity of LLMs to maintain emotional tone through successive rephrasings. These findings offer valuable insights into the design and deployment of LLMs in applications where the preservation of sentiment is crucial, highlighting both the strengths and limitations of current models.