Arthur Melo Cruz
Papers
2
Total Citations
4
H-Index
1
About
Arthur Melo Cruz is a rising scholar at the intersection of artificial intelligence, robotics, and moral philosophy, whose work probes the ethical boundaries of autonomous systems. His research centers on two critical questions: how robots should behave in human-robot interactions, and whether large language models (LLMs) can serve as reliable ethical arbiters. In his most-cited work, "What Should a Robot Do? Comparing Human and Large Language Model Recommendations for Robot Deception" (2024, 3 citations), Cruz conducted a pioneering study that pitted human ethical judgments against LLM outputs across high-risk and low-risk deception scenarios, revealing a surprising alignment in high-stakes contexts. This work has immediate implications for the design of trustworthy AI. His earlier foundational paper, "Case-based robotic architecture with multiple underlying ethical frameworks for human-robot interaction" (2022, 1 citation), tackled the thorny problem of moral pluralism in machines, proposing a novel architecture that allows robots to navigate conflicting ethical theories in real time. Though early in his career, Cruz’s contributions are already shaping debates on machine ethics, offering a pragmatic path toward responsible autonomy.
Research Focus
Key Achievements
Top Papers
- 1
- 2