Date of Award
5-2026
Culminating Project Type
Starred Paper
Styleguide
apa
Degree Name
Computer Science: M.S.
Department
Computer Science and Information Technology
College
School of Science and Engineering
First Advisor
Anda, Andrew A
Second Advisor
Petzold, Mark C
Third Advisor
Gill, Mark C
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
AI Ethics, Ethical AI Framework, Value Alignment, AI safety and governance, Moral reasoning, Machine ethics
Abstract
Artificial intelligence, especially Large Language Models(LLMs), is advancing at a rapid rate, and their impact is increasingly being compared to transformative inventions such as electricity and the internet. This rapid expansion has intensified concern about the absence of a unified ethical foundation for artificial intelligence. Existing approaches, ranging from data-driven moral reasoning and reinforcement-based alignment to safety governance and cultural value mapping, address only fragments of what it means for an AI system to act ethically. This conceptual fragmentation limits the ability of researchers, policymakers, and developers to evaluate or compare AI systems on consistent ethical grounds. This study proposes the Six-Axis Ethical Evaluation Framework (SAEEF), a holistic model for defining and assessing the moral and ethical soundness of AI systems. SAEEF integrates six interrelated dimensions: Moral Reasoning; how models form and justify ethical judgments; Value Alignment; the degree to which learned behavior aligns with human norms and values; Ethical Benchmarks; standardized datasets and evaluative criteria for measuring ethical competence; AI Safety and Governance; the institutional and technical safeguards required for responsible deployment; Human Values and Pluralism; the inclusion of cultural diversity and moral plurality in ethical evaluation; and Epistemic Integrity and Explainability; the faithfulness, transparency, and trustworthiness of model reasoning. Through a synthesis of interdisciplinary literature, this paper argues that ethical AI cannot be adequately understood through isolated metrics or single-domain approaches alone. Instead, moral and ethical reliability must be treated as a multidimensional construct that emerges from the interaction of all six axes. In doing so, SAEEF provides a conceptual foundation for more systematic ethical evaluation and offers a basis for future testing, auditing, and rubric-based assessment of AI systems.
Recommended Citation
Singhal, Shikhar, "Six-Axis Ethical Evaluation Framework (SAEEF)" (2026). Culminating Projects in Computer Science and Information Technology. 68.
https://repository.stcloudstate.edu/csit_etds/68
Comments/Acknowledgements
I would like to express my sincere appreciation to my advisor, Dr. Andrew A. Anda, for their continuous guidance, encouragement, and thoughtful feedback throughout the completion of this starred paper. Their mentorship and academic insight were invaluable in shaping the direction and quality of this work. I am also deeply grateful to my committee members and faculty for their time, support, and constructive suggestions. Their comments and guidance helped strengthen this study and contributed meaningfully to my academic growth. My sincere thanks also go to Saint Cloud State University for providing the resources, learning environment, and opportunities that supported this research. I am thankful as well to my peers and friends for their encouragement and motivation during this process. Finally, I would like to express my heartfelt gratitude to my family for their unwavering support, patience, and encouragement throughout my academic journey. Their belief in me has been a constant source of strength and motivation.