Saved in:
Bibliographic Details
Main Authors: Jotautaite, Monika, Phuong, Mary, Mangat, Chatrik Singh, Martinez, Maria Angelica
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.06324
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912317141155840
author Jotautaite, Monika
Phuong, Mary
Mangat, Chatrik Singh
Martinez, Maria Angelica
author_facet Jotautaite, Monika
Phuong, Mary
Mangat, Chatrik Singh
Martinez, Maria Angelica
contents As large language models (LLMs) increasingly integrate into our daily lives, it becomes crucial to understand their implicit biases and moral tendencies. To address this, we introduce a Moral Foundations LLM dataset (MFD-LLM) grounded in Moral Foundations Theory, which conceptualizes human morality through six core foundations. We propose a novel evaluation method that captures the full spectrum of LLMs' revealed moral preferences by answering a range of real-world moral dilemmas. Our findings reveal that state-of-the-art models have remarkably homogeneous value preferences, yet demonstrate a lack of consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06324
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Stability to Inconsistency: A Study of Moral Preferences in LLMs
Jotautaite, Monika
Phuong, Mary
Mangat, Chatrik Singh
Martinez, Maria Angelica
Computers and Society
Artificial Intelligence
As large language models (LLMs) increasingly integrate into our daily lives, it becomes crucial to understand their implicit biases and moral tendencies. To address this, we introduce a Moral Foundations LLM dataset (MFD-LLM) grounded in Moral Foundations Theory, which conceptualizes human morality through six core foundations. We propose a novel evaluation method that captures the full spectrum of LLMs' revealed moral preferences by answering a range of real-world moral dilemmas. Our findings reveal that state-of-the-art models have remarkably homogeneous value preferences, yet demonstrate a lack of consistency.
title From Stability to Inconsistency: A Study of Moral Preferences in LLMs
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2504.06324