AI still sucks at moderating hate speech

For all of the recent advances in language AI technology, it still struggles with one of the most basic applications. In a new study, scientists tested four of the best AI systems for detecting hate speech and found that all of them struggled in different ways to distinguish toxic and innocuous sentences. The results are…


This entry originally appeared at www.technologyreview.com/2021/06/04/1025742/ai-hate-speech-moderation, and may be a summary or abridged version.