Reflect, Reason, Rephrase (R³-Detox): An In-Context Learning Approach to Text Detoxification

Traditional content moderation, while effective in reducing toxicity through content removal or censoring, can discourage user participation by making them feel restricted or unfairly targeted, especially in nuanced discussions. Text detoxification offers a more constructive alternative by rephrasing offensive language into respectful forms. We propose R3-Detox, a Reflect-Reason-Rephrase framework that structures detoxification into three steps within a single prompt. The model identifies potentially toxic elements guided by Shapley values to reduce fabricated predictions, evaluates overall toxicity, and then revises the text to eliminate toxicity while retaining meaning. We augment three offensive text paraphrasing datasets (ParaDetox, Parallel Detoxification, APPDIA) with explicit detoxification reasoning. Evaluated with in-context learning, R3-Detox outperforms state-of-the-art methods, including instruction following models.