Implicit pen annotation assisted by Large Language Models

In our modern society, integrating humans and computer systems has transformed everyday tasks, including reading, annotating, and reviewing documents. Annotating documents is an age-old practice that involves adding markings and notes to engage with the material. Although this process is crucial for understanding texts and facilitating collaborative communication, it has not evolved significantly over the years. Tedious and repetitive workflows in current digital annotation tools suggest missed opportunities for more intelligent, adaptive design. This work introduces AnnotateGPT, a document annotation tool with a digital pen. It leverages a Large Language Model (LLM) (1) to infer the underlying purposes of the user’s annotations and (2) automatically generates annotations with the same purpose throughout the document. AnnotateGPT aims to alleviate the burdens of manual annotation, enabling users to focus on tasks that require critical expertise.

Name thesis:degree_name

Master of Science (MSc)

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Ontario Institute of Technology

Year dc:date.issued

2025

Author dc:creator

• Leung, Benedict

Advisors dc:contributor.advisor

• Shimabukuro, Mariana
• Collins, Christopher

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10155/1990

OAI identifier oai:identifier

oai:ontariotechu.scholaris.ca:10155/1990