A Roadmap to Impactful Pluralistic Alignment Research Pluralistic alignment is thriving as a research agenda yet failing at its goal: making the AI systems people actually use more pluralistic. We argue adoption in deployed models should be the field's main goal and lay out the research agenda to get there. OvertonBench Benchmarking Overton Pluralism in LLMs A benchmark measuring whether LLMs represent the full spectrum of human viewpoints on contested questions. ICLR 2026. From Dialogue to Decision An LLM-Powered Framework for Analyzing Collective Idea Evolution and Voting Dynamics in Deliberative Assemblies Master's thesis supervised by Deb Roy, MIT Empowering K12 Educators Fostering Collaborative Intelligence with Generative AI Research final project for MIT course MAS.s60 GenAI in K12 Education in Fall 2023. Interplay Between Implicit Bias and Sycophancy in LLMs Implications for Fairness in Educational Decisions Research final project for MIT seminar course 6.S986 "Large Language Models and Beyond" in Spring 2024 with professor Yoon Kim. LLMs for Public Narrative Interpretablity of Language Models Using Category Theory
