To access this work you must either be on the Smith College campus OR have valid Smith login credentials.

On Campus users: To access this work if you are on campus please Select the Download button.

Off Campus users: To access this work from off campus, please select the Off-Campus button and enter your Smith username and password when prompted.

Non-Smith users: You may request this item through Interlibrary Loan at your own library.

Publication Date

2025-5

First Advisor

Alicia M. Grubb

Document Type

Honors Project

Degree Name

Bachelor of Arts

Department

Computer Science

Keywords

formal logic, human-centric AI, large language models (LLMs), accessibility, linear temporal logic (LTL), explainability, requirements engineering

Abstract

Formal methods and notations in requirements engineering have been used for decades, but they are rarely applied unless mandated by certifications. Their complexity makes them difficult for non-experts, such as novices and non-technical stakeholders in multidisciplinary teams, to interpret and apply effectively. To enable broader participation in collaborative software development and support novices in gaining expertise, we propose leveraging artificial intelligence (AI) to assist in interpreting formal notations. Our research explores how generative AI, specifically large language models (LLMs), can aid practitioners and novices in understanding formal requirements. In this thesis, we conduct an exploratory study on translating and interpreting linear temporal logic (LTL) formulas. First, we investigate how LLMs can generate descriptions of LTL formulas by providing them with detailed information about LTL syntax and semantics. Next, we conduct a classroom study in which students learn LTL and then interpret a series of LTL formulas with and without the aid of LLM-generated descriptions. We evaluate the accuracy of their responses, their comprehension of the explanations, and their perception of the usefulness of AI-generated support. Finally, based on insights from the classroom study, we refine our approach by improving our prompt and assessing the overall effectiveness and clarity of the explanations it generates.

Rights

©2025 Sonora Halili. Access limited to the Smith College community and other researchers while on campus. Smith College community members also may access from off-campus using a Smith College log-in. Other off-campus researchers may request a copy through Interlibrary Loan for personal use.

Language

English

Comments

[7], 39, [3] pages : color charts. Includes bibliographical references.

Download

Smith Only:
Off Campus Download

Share

COinS