HONEST: Measuring Hurtful Sentence Completion in Language Models
Debora Nozza, Federico Bianchi, Dirk Hovy · 2021
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 and genderspecific patterns.We propose a score to measure hurtful sentence completions in language models (HONEST).It uses a systematic template-and lexicon-based bias evaluation methodology for six languages.Our findings suggest that these models replicate and amplify deep-seated societal stereotypes about gender roles.Sentence completions refer to sexual promiscuity when the target is female in 9% of the time, and in 4% to homosexuality when the target is male.The results raise questions about the use of these models in production settings.