Morally Programmed LLMs Reshape Human Morality

Read full text Summarise with VIRAT
Authors: Pengzhao Lyu, Dean Y.J. Kim, Yingyue Luna Luan, Jungmin Choi
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

As large language models (LLMs) increasingly participate in high-stakes decision-making, a central societal debate has revolved around which moral frameworks—deontological or utilitarian—should guide machine behavior. However, a largely overlooked question is whether the moral principles that humans encode in LLMs could, through repeated interactions, reshape human moral inclinations. We developed two LLMs programmed with either deontological principles (D-LLM) or utilitarian principles (U-LLM) and conducted two pre-registered experiments involving extensive human-LLM interactions: 15,985 total exchanges across the two experiments. Results show that interacting with these morally programmed LLMs systematically shifted human moral inclinations to align with the principles embedded in these systems. These effects remained strong two weeks after the interaction, with only slight decay, suggesting deep internalization rather than superficial agreement. Further, LLM-induced shifts in human moral inclinations translated into meaningful changes in socio-political policy evaluations, shaping how individuals approach contentious social issues. Overall, these results demonstrate that morally programmed LLMs can shape—not merely reflect—human morality, revealing a critical design paradox: embedding moral principles in LLMs not only restricts their behavior but also poses the risk of shaping human morality, raising important ethical and policy questions about who determines which principles intelligent machines should adhere to.

Fields of Study & Subjects

Ethics and Social Impacts of AI Psychology of Moral and Emotional Judgment Ethics in Business and Education

Publication details

Journal / source
PsyArXiv (OSF Preprints)
Publication date
22 March 2026
Language
EN
Document type
Preprint