Shistata Subedi is a Ph.D. student at the University of Oregon, currently working with Prof. Suyash Gupta on decentralized systems and blockchain infrastructure. Over the past year, Shistata has worked on two orthogonal yet complementary research projects. Her primary research focuses on designing efficient storage data structures for decentralized systems. Specifically, she is developing mechanisms that enable verifiable range queries using segment trees, allowing users to access historical transaction states on decentralized ledgers efficiently.
In parallel, she has also explored the field of Explainable AI (XAI), working to improve the interpretability and transparency of large language models (LLMs). In this work, she designed an LLM capable of detecting and explaining anomalies in the behavior of another LLM, such as a semantic analysis chatbot, advancing the broader goals of responsible and trustworthy AI.
Before starting graduate school, she worked as a software developer. This hands-on experience taught her a lot about building real-world systems, which helps her think about practical solutions in my research.
