Tanmay Parekh, a fourth-year Ph.D. student in the Computer Science department at UCLA, has been awarded the prestigious Bloomberg Data Science Ph.D. Fellowship for the academic year 2025-2026. This fellowship recognizes and supports up to ten outstanding doctoral students in their research and professional development in the fields of artificial intelligence, machine learning, and natural language processing. Tanmay is co-advised by Professor Nanyun Peng and Professor Kai-Wei Chang and is part of the PlusLab and UCLA NLP Groups. His research focuses on building information extraction systems capable of automatically removing structured information from unstructured or semi-structured text. He specializes in building generalizable systems capable of scaling across a wide range of languages and different domains for broader social applications by enhancing the reasoning skills of Large Language Models (LLMs). His work on SPEED and SPEED++, which build large-scale multilingual event extraction framework capable of detecting epidemic-related information from social media tweets across a wide range of languages and diseases, has been one of his prominent research projects. He also shows how this framework can be utilized practically for automatic early detection of epidemics and misinformation detection. His works have been accepted at the prominent conferences of North American Chapter of the Association for Computational Linguistics (NAACL 2024) and Empirical Methods in Natural Language Processing (EMNLP 2024). Moving forward, Tanmay plans to work on further enhancing the generalizability of Information Extraction systems by exploring domain-specialized and multilingual data generation. He’s also exploring methods to unify the open-generation LLMs with closed-trained supervised models.