Language models have revolutionized the field of NLP. However, language models capture and proliferate hurtful stereotypes, especially in text generation. Our results show that 4.3% of the time, language models complete a sentence with a hurtful word. These cases are not random, but follow language ...
Highlights, strengths & weaknesses, commercial applications, and societal impact — written for this paper on demand.
Research Assistant
AI chat, annotations, notes & similar papers
No comments yet
Be the first to share your thoughts!