4 papers
Measuring Validity in LLM-based Resume Screening
Jane Castleman, Zeyu Shen, Blossom Metevier +2
Resume screening is perceived as a particularly suitable task for LLMs given their ability to analyze natural language; thus many entities rely on general purpose LLMs without furt…
The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
Max Springer, Chung Peng Lee, Blossom Metevier +5
Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial…
Adultification Bias in LLMs and Text-to-Image Models
Jane Castleman, Aleksandra Korolova
The rapid adoption of generative AI models in domains such as education, policing, and social media raises significant concerns about potential bias and safety issues, particularly…
Why am I Still Seeing This: Measuring the Effectiveness Of Ad Controls and Explanations in AI-Mediated Ad Targeting Systems
Jane Castleman, Aleksandra Korolova
Recently, Meta has shifted towards AI-mediated ad targeting mechanisms that do not require advertisers to provide detailed targeting criteria, likely driven by excitement over AI c…