565 citations · 979 across the 85 of their papers we have counts for
6 papers · 1 filter
Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection
Maarten Sap, Swabha Swayamdipta, Laura Vianna +3
The perceived toxicity of language can vary based on someone's identity and beliefs, but this variation is often ignored when collecting toxic language datasets, resulting in datas…
Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts
Ashutosh Baheti, Maarten Sap, Alan Ritter +1
Dialogue models trained on human conversations inadvertently learn to generate toxic responses. In addition to producing explicitly offensive utterances, these models can also impl…
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
Alisa Liu, Maarten Sap, Ximing Lu +4
Despite recent advances in natural language generation, it remains challenging to control attributes of generated text. We propose DExperts: Decoding-time Experts, a decoding-time…
Detoxifying Language Models Risks Marginalizing Minority Voices
Albert Xu, Eshaan Pathak, Eric Wallace +3
Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020;…
Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines
Saadia Gabriel, Skyler Hallinan, Maarten Sap +4
Even to a simple and short news headline, readers react in a multitude of ways: cognitively (e.g. inferring the writer's intent), emotionally (e.g. feeling distrust), and behaviora…
Challenges in Automated Debiasing for Toxic Language Detection
Xuhui Zhou, Maarten Sap, Swabha Swayamdipta +2
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investiga…