Nick Crispino

I am an undergraduate student at Washington University in St. Louis, where I am part of the McKelvey School of Engineering and work on natural language processing. I am in the WashU NLP Group, advised by Professor Chenguang Wang.

I have also been a teaching assistant for a variety of computer science classes: CSE131, our introduction to computer science course (6 semesters); CSE347, our algorithms course (1 semester); CSE 527A, our graduate-level natural language processing course (1 semester).

GitHub  /  Twitter

profile photo


I'm interested in improving the performance of large language models, exploring open-source models and methods, and applying these models to other domains (e.g., crypto).

project image

Agent Instructs Large Language Models to be General Zero-Shot Reasoners

Nicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, Chenguang Wang
arXiv preprint, 2023
arxiv / code /

Zero-shot AgentInstruct uses an agent to generate dataset-specific instructions to improve the zero-shot performance of instruction-following large language models.

Other Projects

These include coursework, side projects and unpublished research work.

Design and source code from Jon Barron's website. Template taken from Leonid Keselman.