Saved in:
Bibliographic Details
Main Authors: Kim, Jiseon, Kwon, Jea, Vecchietti, Luiz Felipe, Oh, Alice, Cha, Meeyoung
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.10886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913794868903936
author Kim, Jiseon
Kwon, Jea
Vecchietti, Luiz Felipe
Oh, Alice
Cha, Meeyoung
author_facet Kim, Jiseon
Kwon, Jea
Vecchietti, Luiz Felipe
Oh, Alice
Cha, Meeyoung
contents Deploying large language models (LLMs) with agency in real-world applications raises critical questions about how these models will behave. In particular, how will their decisions align with humans when faced with moral dilemmas? This study examines the alignment between LLM-driven decisions and human judgment in various contexts of the moral machine experiment, including personas reflecting different sociodemographics. We find that the moral decisions of LLMs vary substantially by persona, showing greater shifts in moral decisions for critical tasks than humans. Our data also indicate an interesting partisan sorting phenomenon, where political persona predominates the direction and degree of LLM decisions. We discuss the ethical implications and risks associated with deploying these models in applications that involve moral decisions.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10886
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
Kim, Jiseon
Kwon, Jea
Vecchietti, Luiz Felipe
Oh, Alice
Cha, Meeyoung
Computers and Society
Artificial Intelligence
Computation and Language
Deploying large language models (LLMs) with agency in real-world applications raises critical questions about how these models will behave. In particular, how will their decisions align with humans when faced with moral dilemmas? This study examines the alignment between LLM-driven decisions and human judgment in various contexts of the moral machine experiment, including personas reflecting different sociodemographics. We find that the moral decisions of LLMs vary substantially by persona, showing greater shifts in moral decisions for critical tasks than humans. Our data also indicate an interesting partisan sorting phenomenon, where political persona predominates the direction and degree of LLM decisions. We discuss the ethical implications and risks associated with deploying these models in applications that involve moral decisions.
title Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
topic Computers and Society
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2504.10886