Blog tagged as Bias

Study Uncovers Bias in AI Text Detectors Against Non-Native Writers
A new study reveals troubling bias in AI detectors of machine-generated text against non-native English speakers. The findings raise important questions around AI fairness and underscore the need for more inclusive technologies.
Ines Almeida
13.08.23 05:47 AM - Comment(s)
Reading Between the Lines: Subtle Stereotypes in AI Text Generation
Recent advances in AI language models like GPT-4 and Claude 2 have enabled impressively fluent text generation. However, new research reveals these models may perpetuate harmful stereotypes and assumptions through the narratives they construct.
Ines Almeida
10.08.23 07:59 AM - Comment(s)
Tracking Political Bias from Data to Models to Decisions
Measuring the political leaning of various pretrained LMs.
Ines Almeida
10.08.23 07:57 AM - Comment(s)