"Mitigating harm in language models with conditional-likelihood filtration."

Helen Ngo et al. (2021)

> Home

Details and statistics

DOI: —

access: open

type: Informal or Other Publication

metadata version: 2021-08-20

- view
  - electronic edition @ arxiv.org (open access)
- export record
  dblp key:
  - journals/corr/abs-2108-07790
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2108-07790
Helen Ngo, Cooper Raterink, João G. M. Araújo, Ivan Zhang, Carol Chen, Adrien Morisot, Nicholas Frosst:
Mitigating harm in language models with conditional-likelihood filtration. CoRR abs/2108.07790 (2021)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.