Safety and Fairness for Content Moderation in Generative Models.
Susan HaoPiyush KumarSarah LaszloShivani PoddarBhaktipriya RadharapuRenee ShelbyPublished in: CoRR (2023)
Keyphrases
- generative model
- probabilistic model
- discriminative learning
- prior knowledge
- mixture model
- conditional random fields
- hierarchical hidden markov models
- discriminative models
- maximum entropy principle
- topic models
- semi supervised
- em algorithm
- generative and discriminative models
- hidden variables
- graphical models
- maximum entropy
- object categories
- bayesian networks
- representational power
- naive bayes models
- training data