First Advisor

Ameeta Agrawal

Date of Award

Winter 3-22-2025

Document Type

Thesis

Degree Name

Bachelor of Science (B.S.) in Computer Science and University Honors

Department

Computer Science

Language

English

Subjects

Computer Science, Large Language Models, Artificial Intelligence, Natural Language Processing, Machine Learning

Abstract

This research delves into the realm of "protective scenes" within Large Language Models (LLMs), exploring their impact on bias mitigation, deception, and context preservation. The study investigates the use of roleplay prompting human-like behavior and reasoning in LLMs, focusing on the Character-LLM framework's concept of protective scenes with graduated levels of protection. By combining insights from psychology, cognitive science, and computational analysis, this research aims to develop a framework for understanding how protective scenes influence roleplay performance in LLMs, ultimately contributing to the development of more reliable and ethical AI systems.

Persistent Identifier

https://archives.pdx.edu/ds/psu/43136

Share

COinS