AI Safety and Reliability Research at UC Merced
Research on the safety and reliability of large language models in safety-critical systems.
At UC Merced, I conducted research on the safety and reliability of large language models in safety-critical systems under Professor Ayush Pandey.
The work focused on identifying and mitigating hallucinations in AI outputs, with applications in areas such as healthcare diagnostics and cybersecurity.
I developed evaluation frameworks, tested model behavior across edge cases, and analyzed the risks of deploying AI in mission-critical environments.
This research highlighted the importance of precision, trustworthiness, and interpretability in advancing the safe adoption of AI technologies.
