Greg Durrett

Greg Durrett is an Associate Professor in the Computer Science Department at New York University, affiliated with the Courant Institute and the Center for Data Science. His research focuses on Natural Language Processing and machine learning, particularly on improving large language models (LLMs) for real-world applications. His work includes enhancing LLMs' reasoning capabilities and assessing their performance in areas like medical information processing and scientific discovery. Durrett has published in top conferences such as NeurIPS, EMNLP, and ICLR. He teaches courses on natural language processing and LLM reasoning at NYU and has previously taught at the University of Texas at Austin. His research group, the TAUR lab, explores methods to make LLMs more reliable and effective.

Greg Durrett is an Associate Professor of Computer Science at New York University, specializing in Natural Language Processing. His research focuses on improving the effectiveness and reliability of language models through tasks such as summarization, evaluation, and reasoning. He has explored challenges in generating factually accurate outputs, particularly in domains like medicine, and has investigated methods to enhance model calibration and explainability. His work also includes advancements in coreference resolution, entity linking, and neural parsing, with an emphasis on syntactic and semantic modeling. Durrett's contributions aim to address gaps in current language model capabilities, especially in handling complex reasoning and factual consistency.