Automation of road safety literature scanning using LLMs
WACRSR operates as
a research institute for conducting new and innovative approaches to road safety.
Importantly, we also produce a lot of information for the general public and the Road Safety Commission. Part of what we do involves keeping on top of the literature by scanning recent road safety journals for information relevant to our centre and the Road Safety Commission. Screening these articles for specific relevance takes a substantial amount of time and is able to be at least partially automated, cutting human time on task.
The aim of this project will be to utilise Large Language Models (Claude, chatGPT, Llama3) to score articles on their relevance (and other factors) and then summarise the recent road safety literature from a specific set of journals. Ideally, a customisable interface in Python, javascript, or other language would be developed making interfacing with the automated literature scan easier, along with exporting the scan into a spreadsheet to deliver to relevant stakeholders.
Client
Contact: Matthew Albrecht
Phone: 0481228718
Email: [email protected]
Preferred contact: Email
Location: Crawley Campus - Maths Link
IP Exploitation Model
The IP exploitation model requested by the Client is: Creative Commons (open source) http://creativecommons.org.au/
Department of Computer Science & Software Engineering
The University of Western Australia
Last modified: 16 July 2024
Modified By: Michael Wise
|
![UWA](http://teaching.csse.uwa.edu.au/units/CITS3200/project/UWA-Full-Hor-CMYK.jpg) |