Research Statement: My research focus is the broader ecosystem of AI’s societal impact, with a primary focus on alignment, safety, and the downstream effects of AI technologies. On the technical front, I focus on creating and analyzing computational methods to address human-centered challenges in AI, such as controllable text generation and alignment with human preferences. By combining theoretical rigor with practical applications, my aim is to develop AI systems that are not only innovative but also socially beneficial. Beyond advancing methodologies, I am interested in exploring broader societal questions, such as how biases in AI models influence human decision-making and behavior, emphasizing the urgent need for responsible AI development. Lastly, I try to approach my research through an interdisciplinary lens, drawing on insights from fields like NLP, psychology, and political science.