11 citations · 28 across the 8 of their papers we have counts for
8 papers
Evaluation of African American Language Bias in Natural Language Generation
Nicholas Deas, Jessi Grieser, Shana Kleiner +3
We evaluate how well LLMs understand African American Language (AAL) in comparison to their performance on White Mainstream English (WME), the encouraged "standard" form of English…
SafeText: A Benchmark for Exploring Physical Safety in Language Models
Sharon Levy, Emily Allaway, Melanie Subbiah +4
Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such typ…
Mitigating Covertly Unsafe Text within Natural Language Systems
Alex Mei, Anisha Kabir, Sharon Levy +7
An increasingly prevalent problem for intelligent technologies is text safety, as uncontrolled systems may generate recommendations to their users that lead to injury or life-threa…
Detecting and Reducing Bias in a High Stakes Domain
Ruiqi Zhong, Yanda Chen, Desmond Patton +2
Gang-involved youth in cities such as Chicago sometimes post on social media to express their aggression towards rival gangs and previous research has demonstrated that a deep lear…
An Overview of Computational Approaches for Interpretation Analysis
Philipp Blandfort, Jörn Hees, Desmond U. Patton
It is said that beauty is in the eye of the beholder. But how exactly can we characterize such discrepancies in interpretation? For example, are there any specific features of an i…
Detecting Gang-Involved Escalation on Social Media Using Context
Serina Chang, Ruiqi Zhong, Ethan Adams +6
Gang-involved youth in cities such as Chicago have increasingly turned to social media to post about their experiences and intents online. In some situations, when they experience…