Kyle Montgomery

Welcome! My name is Kyle Montgomery, and I graduate student in computer science at Washington University in St. Louis. I will graduate in May, 2024. Broadly speaking, my interests include software developement, machine learning, and rock climbing 🧗. I am also a member of WASHU’s NLP group, advised by Prof. Chenguang Wang.

My research mostly focuses on large language models. Specifically, I’m working on projects related to language agents, prompting, saftey, and various applications of LLMs.

selected publications

AgentInstruct

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

Nicholas Crispino, Kyle Montgomery, Fankun Zeng, and 2 more authors

2023

Abs HTML PDF

We introduce a method to improve the zero-shot reasoning abilities of large language models on general language understanding tasks. Specifically, we build an autonomous agent to instruct the reasoning process of large language models. We show this approach further unleashes the zero-shot reasoning abilities of large language models to more tasks. We study the performance of our method on a wide set of datasets spanning generation, classification, and reasoning. We show that our method generalizes to most tasks and obtains state-of-the-art zero-shot performance on 20 of the 29 datasets that we evaluate. For instance, our method boosts the performance of state-of-the-art large language models by a large margin, including Vicuna-13b (13.3%), Llama-2-70b-chat (23.2%), and GPT-3.5 Turbo (17.0%). Compared to zero-shot chain of thought, our improvement in reasoning is striking, with an average increase of 10.5%. With our method, Llama-2-70b-chat outperforms zero-shot GPT-3.5 Turbo by 10.2%.