New papers on Safety, alignment & fairness
1 new papers on safety, alignment & fairness in the last 7 days, within AI & machine learning. These are the 1 Pipette rates most worth reading, with the main result in the authors' own words.
The best of the week
Automating inequality? Gender bias in AI-mediated labor markets
We find that LLMs generate gender-stereotypical CVs and exhibit gender bias in screening scores and wage recommendations.
Peer-reviewed journalReal-world use