Toxicity in language models is disproportionately encoded in early MLP layers and can be localized via activation differentials then suppressed at inference time without gradient descent.
Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
Toxicity in language models is disproportionately encoded in early MLP layers and can be localized via activation differentials then suppressed at inference time without gradient descent.
- LLM Harms: A Taxonomy and Discussion