Pavements, Active

Adaptation of a Large Language Model

The goal is to create an Artificial Intelligence (AI) model that can process and generate natural language to answer common pavement engineering and pavement construction questions quickly and accurately. The model will be able to answer questions about pavement design, mix design, specifications, best construction practices, pavement maintenance and rehabilitation, pavement management, as well as pavement testing and evaluation. It will have a human-like ability to provide reliable answers and will be suitable for interactive training. The tool will have the capability to assess a user's knowledge by posing questions and offering feedback on their answers, making it an effective tool for skill development and evaluation. Additionally, the model will be able to assist pavement engineers in retrieving and summarizing relevant information from a large corpus of pavement-related literature. This can facilitate knowledge discovery and help pavement engineers stay up-to-date with the latest developments in their field.

Contacts

Dr. Lev Khazanovich
lev.k@pitt.edu

The IRISE Consortium is a pioneering initiative aimed at addressing the durability and resiliency challenges of aging highway infrastructure.

3700 O'Hara Street
Pittsburgh, PA 15261

Contact IRISE