Research
I research how networked systems (cloud infrastructure, social media platforms, AI/LLM-based systems) impact society through three interconnected lenses:
Clinical AI & Digital Health - Researching the intersection of AI and clinical judgment across the full clinical reasoning pipeline. Through randomized controlled trials and behavioral studies, my work examines how LLMs support diagnosis, triage, management reasoning, and risk stratification, how physicians adopt and over-rely on AI (automation bias), and how clinical AI can advance health equity in low-middle-income countries, bridging technical innovation with real-world clinical impact.
Digital Development - Examining how technology design and implementation can advance inclusive growth in underserved communities, creating sustainable pathways for economic and social advancement while bridging persistent digital divides. This includes fostering trust in digital information ecosystems through solutions spanning evidence-based media literacy, misinformation interventions, and multimodal detection of harmful online content.
Trustworthy AI Systems — Scaling AI responsibly, from efficient training to autonomous agentic systems, demands reliability and resistance to misuse. My work tackles this across three fronts: reducing data and compute costs through pruning and active learning; understanding and mitigating failure modes in LLMs and agentic AI systems (e.g., overconfidence, unsafe autonomous behavior); and building robust detection systems for deepfakes and synthetic media.
At the Internet, Data, and Society Lab (IDSL) at LUMS, I lead initiatives combining approaches like generative AI and privacy-preserving machine learning with rigorous social science methods, including randomized controlled trials. By bridging computational and human-centered perspectives, my work aims to develop digital technologies that serve diverse communities equitably while addressing critical considerations of accessibility, sustainability, and responsible innovation.
