View Proposal

Proposer
Abdullah Almasri
Title
Comparative Analysis of LLM vs. Human-Written Summaries for Scientific Articles.
Goal
To evaluate how effectively LLM-generated summaries compare to human-written summaries of scientific articles.
Description
The task is to use LLMs to generate summaries of scientific articles and compare them to summaries authored by human experts; evaluate the effectiveness of LLM-generated summaries based on criteria such as completeness, clarity, and accuracy; and identify the strengths and weaknesses in LLMs' summarization capabilities.
Resources
Large Language Models
Background
Software Development, Machine Learning, NLP.
Url
Difficulty Level
Moderate
Ethical Approval
InterfaceOnly
Number Of Students
2
Supervisor
Abdullah Almasri
Keywords
machine learning, large language models, natural language processing (nlp), text summarization, text minning
Degrees
Bachelor of Science in Computing Science
Back to List