72 citations · 116 across the 8 of their papers we have counts for
4 papers · 1 filter
Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading
Evan Crothers, Herna Viktor, Nathalie Japkowicz
A common approach to quantifying neural text classifier interpretability is to calculate faithfulness metrics based on iteratively masking salient input tokens and measuring change…
In BLOOM: Creativity and Affinity in Artificial Lyrics and Art
Evan Crothers, Herna Viktor, Nathalie Japkowicz
We apply a large multilingual language model (BLOOM-176B) in open-ended generation of Chinese song lyrics, and evaluate the resulting lyrics for coherence and creativity using huma…
Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods
Evan Crothers, Nathalie Japkowicz, Herna Viktor
Machine generated text is increasingly difficult to distinguish from human authored text. Powerful open-source models are freely available, and user-friendly tools that democratize…
Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers
Evan Crothers, Nathalie Japkowicz, Herna Viktor +1
The detection of computer-generated text is an area of rapidly increasing significance as nascent generative models allow for efficient creation of compelling human-like text, whic…