Abusive text transformation using LLMs
This addresses the need for safer online content by filtering hate speech and swear words in tweets and reviews, but it is incremental as it applies existing LLMs to a specific text transformation task.
The study tackled the problem of transforming abusive text into non-abusive versions while preserving intent, using LLMs like Gemini, GPT-4o, DeepSeek, and Groq, with results showing Groq produced vastly different outcomes compared to others.
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.