Concepedia

Detoxifying Language Models Risks Marginalizing Minority Voices

Albert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, Dan Klein

2021 · 58 citations · 17 references

DOIFull text

Open access

Concepts

Abstract

Albert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, Dan Klein. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

References

17

Undoing Appropriateness: Raciolinguistic Ideologies and Language Diversity in Education

Nelson Flores, Jonathan Rosa · Harvard Educational Review · 2015 · 2.6K citations

, , +17

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Taylor Shin, Yasaman Razeghi, Robert L. Logan et al. · 2020 · 1.2K citations · Full text

, , +16

Hierarchical Neural Story Generation

Angela Fan, Mike Lewis, Yann Dauphin · 2018 · 1.1K citations · Full text

, , +15

CTRL: A Conditional Transformer Language Model for Controllable Generation

Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney et al. · arXiv (Cornell University) · 2019 · 790 citations · Full text

, , +15

The Risk of Racial Bias in Hate Speech Detection

Maarten Sap, Dallas Card, Saadia Gabriel et al. · 2019 · 771 citations · Full text

, , +15