In today's world, digital technologies are increasingly mediated by artificial intelligence systems whose inner workings are complex and often opaque, raising important questions about their societal impact. Our group brings together strong computational and engineering expertise to study the safety and integrity of online ecosystems. Our work combines scalable computational methods with causal experimental designs to audit algorithmic systems, assess the safety of information exposure across digital platforms, and evaluate the risks posed by large language models—from adversarial vulnerabilities to persuasive capabilities. By studying the complex interactions between algorithms and human behavior, we aim to understand how digital technologies shape information exposure, public discourse, and societal outcomes.
Studies of Large Language Models
LLM Red Teaming & Safety
Adversarial testing and safety evaluation of large language models.
Agentic AI Persuasions
Understanding AI agents' persuasive capabilities.
LLM-Mediated Information Systems
How large language models reshape information exposure and consumption.
Studies of Sociotechnical Systems
Prevalence of Problematic Content
Comprehensive evaluation of AI systems in real-world deployment contexts.
Counterfactual Experiment Design
Causal inference frameworks for auditing algorithmic systems.
Studies of Information Ecosystems
Our Shared Reality
Information ecosystem — mainstream.
Media Fragmentation Analysis
Cross-platform information consumption patterns.
Computational Methods
Statistical Inference on Networks
Developing robust measurement frameworks for online discourse.
Open-World Detection and Inference at Scale
Detection and prediction methods for large-scale real-world data under minimal supervision.