The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.
Workshop on NLP for Positive Impact at ACL - IJCNLP
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2021 1verdicts
ACCEPT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Ethical and social risks of harm from Language Models
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.