projects

[Plan*RAG] I study how causality and other formal reasoning systems can improve AI reasoning and help solve complex problems that require exploration over thousands of steps. See Plan*RAG for an example: how solving complex tasks can be abstracted out as planning over a directed acyclic graph (DAG).

[DoWhy, PyWhy] Unlike prediction, causal inference depends critically on assumptions: "no causes in, no causes out". To help researchers formally state and verify causal assumptions, I built DoWhy, an open-source Python library that is widely used across industry and academia. I now work on methods to improve the state-of-the-art for verification and robustness tests in causal inference.

[DiCE] Just like medical treatments or economic policies, AI systems can be considered as interventions in our society. I build methods to help experts interpret an AI system's output and estimate their (differential) impact on different subpopulations. One of these methods, Diverse Counterfactual Explanations (DiCE), has been integrated as a part of Microsoft's Responsible AI platform.

[MindNotes app] I am passionate about using technology for greater social good. As one focus, I have worked on improving mental health outreach and support through technology. I also work on how machine learning systems can be used to optimize the reach or impact of societal interventions.