Abusive text transformation using LLMs

TL;DR

This paper explores using large language models to transform abusive text into non-abusive versions while preserving original intent, evaluating multiple models' effectiveness in maintaining sentiment and semantics.

Contribution

It introduces a novel application of LLMs for abusive text transformation and compares the performance of several state-of-the-art models in this task.

Findings

Groq produces significantly different transformation results.

GPT-4o and DeepSeek-V3 show similar performance.

Transformed texts retain sentiment and semantics effectively.

Abstract

Although Large Language Models (LLMs) have demonstrated significant advancements in natural language processing tasks, their effectiveness in the classification and transformation of abusive text into non-abusive versions remains an area for exploration. In this study, we aim to use LLMs to transform abusive text (tweets and reviews) featuring hate speech and swear words into non-abusive text, while retaining the intent of the text. We evaluate the performance of two state-of-the-art LLMs, such as Gemini, GPT-4o, DeekSeek and Groq, on their ability to identify abusive text. We them to transform and obtain a text that is clean from abusive and inappropriate content but maintains a similar level of sentiment and semantics, i.e. the transformed text needs to maintain its message. Afterwards, we evaluate the raw and transformed datasets with sentiment analysis and semantic analysis. Our results show Groq provides vastly different results when compared with other LLMs. We have identified similarities between GPT-4o and DeepSeek-V3.