6 papers
Can AI Agents Synthesize Scientific Conclusions?
Hayoung Jung, Pedro Viana Diniz, José Reinaldo Corrêa Roveda +5
Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their ability to do so in high-stakes d…
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…
Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation
Navreet Kaur, Hoda Ayad, Hayoung Jung +3
Language model users often embed personal and social context in their questions. The asker's role -- implicit in how the question is framed -- creates specific needs for an appropr…
ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
Mahika Phutane, Hayoung Jung, Matthew Kim +2
Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with…
MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform
Hayoung Jung, Shravika Mittal, Ananya Aatreya +3
Understanding the prevalence of misinformation in health topics online can inform public health policies and interventions. However, measuring such misinformation at scale remains…
Algorithmic Behaviors Across Regions: A Geolocation Audit of YouTube Search for COVID-19 Misinformation Between the United States and South Africa
Hayoung Jung, Prerna Juneja, Tanushree Mitra
Despite being an integral tool for finding health-related information online, YouTube has faced criticism for disseminating COVID-19 misinformation globally to its users. Yet, prio…