Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Navrati Saxena
Second Advisor
Christopher Pollett
Third Advisor
Abhishek Roy
Keywords
Admission System Automation, Large Language Models, Natural Language Processing, Bias Mitigation, PDF parsing
Abstract
Admission season places significant demands on university committees, necessitating the review of vast arrays of documents to assess students’ competence. This project advances the development of an automated system designed to streamline this process by evaluating application materials such as Letters of Recommendation (LoRs), Statements of Purpose (SoPs), and resumes. Utilizing a variety of advanced Natural Language Processing (NLP) techniques, the system compares the performance of several Large Language Model (LLM) approaches. It also experiments with different data handling strategies, including the use of vector stores versus traditional context-based processing, to optimize model efficiency and accuracy. Special attention is given to adhering to Proposition 209, ensuring evaluations are conducted without bias regarding race, sex, or ethnicity. By automating the extraction and analysis of applicant information, the system allows for faster, more accurate decision-making, transforming how universities handle admissions.
Recommended Citation
Karri, Sree Hari, "Leveraging Large Language Models for Transforming Student Information into Actionable Data" (2024). Master's Projects. 1436.
https://scholarworks.sjsu.edu/etd_projects/1436
