3 papers
cs.CY2026
Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains
Emaan Bilal Khan, Amy Winecoff, Miranda Bogen +1
Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety proper…
cs.HC2026
Navigating Uncertainties: How GenAI Developers Document Their Models on Open-Source Platforms
Ningjing Tang, Megan Li, Amy Winecoff +3
Model documentation plays a crucial role in promoting transparency and responsible development of AI systems. With the rise of Generative AI (GenAI), open-source platforms have inc…
cs.HC2025
From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating Disorders
Amy Winecoff, Kevin Klyman
Generative AI systems may pose serious risks to individuals vulnerable to eating disorders. Existing safeguards tend to overlook subtle but clinically significant cues, leaving man…