Original Paper: https://arxiv.org/abs/2308.05596
By: Xinlei He, Savvas Zannettou, Yun Shen, Yang Zhang
Abstract:
The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of the problem, research focuses on developing solutions to detect toxic content, usually leveraging machine learning (ML) models trained on human-annotated datasets. While these efforts are important, these models usually do not generalize well and they can not cope with new trends (e.g., the emergence of new toxic terms). Currently, we are witnessing a shift in the approach to tackling societal issues online, particularly leveraging large language models (LLMs) like GPT-3 or T5 that are trained on vast corpora and have strong generalizability. In this work, we investigate how we can use LLMs and prompt learning to tackle the problem of toxic content, particularly focusing on three tasks; 1) Toxicity Classification, 2) Toxic Span Detection, and 3) Detoxification. We perform an extensive evaluation over five model architectures and eight datasets demonstrating that LLMs with prompt learning can achieve similar or even better performance compared to models trained on these specific tasks. We find that prompt learning achieves around 10\% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0.643 vs. 0.640 in terms of F1-score). Finally, for the detoxification task, we find that prompt learning can successfully reduce the average toxicity score (from 0.775 to 0.213) while preserving semantic meaning.
The internet is a vast space that, unfortunately, includes toxic content. This poses a significant challenge for platforms aiming to foster healthy online communities. Traditional methods of detecting and moderating toxic content often fall short due to the evolving nature of internet slang and the subtleties within harmful content.
However, the emergence of Large Language Models (LLMs) like GPT-3 and T5, equipped with prompt learning, is revolutionizing how we approach content moderation.
This blog post explores how LLMs are making online spaces safer and more inclusive through their ability to effectively identify and mitigate toxic content.
Toxic content encompasses bullying, harassment, hate speech, and more, threatening the integrity and inclusiveness of online platforms.
Traditional detection methods, which rely on datasets annotated by humans, struggle to keep up with the dynamic nature of language, often missing new phrases or subtle toxic nuances.