toxicity

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts
Using expert and anti-expert LMs to rewrite toxic text for safety
Skyler Hallinan, Alisa Liu, Yejin Choi, Maarten Sap
Paper BibTeX
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
Steering open-ended text generation toward desired or away from undesired attributes, using expert and anti-expert language models
Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A. Smith, Yejin Choi
Paper BibTeX Code Slides News