Detoxifying Language Models Risks Marginalizing Minority Voices NAACL

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

All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text ACL IJCNLP

Elizabeth Clark | Tal August | Sofia Serrano | Nikita Haduong | Suchin Gururangan | Noah A. Smith |

Expected Validation Performance and Estimation of a Random Variable’s Maximum EMNLP Findings

Jesse Dodge | Suchin Gururangan | Dallas Card | Roy Schwartz | Noah A. Smith |

Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks ACL

Suchin Gururangan | Ana Marasović | Swabha Swayamdipta | Kyle Lo | Iz Beltagy | Doug Downey | Noah A. Smith |

RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models EMNLP Findings

Samuel Gehman | Suchin Gururangan | Maarten Sap | Yejin Choi | Noah A. Smith |

Show Your Work: Improved Reporting of Experimental Results EMNLP

Jesse Dodge | Suchin Gururangan | Dallas Card | Roy Schwartz | Noah A. Smith |

Variational Pretraining for Semi-supervised Text Classification ACL

Suchin Gururangan | Tam Dang | Dallas Card | Noah A. Smith |

Annotation Artifacts in Natural Language Inference Data NAACL

Suchin Gururangan | Swabha Swayamdipta | Omer Levy | Roy Schwartz | Samuel Bowman | Noah A. Smith |