Virtue Profiles and Value-Aligned Actions in Language Model Decision-Making

A Study of Cardinal Virtue Conditioning and Value-Action Alignment in LLMs

Bachelor Thesis (2026)
Author(s)

R.H. Schnell (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

A. Homayounirad – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

L. Cavalcante Siebert – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

C.A. Raman – Graduation committee member (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2026
Language
English
Graduation Date
25-06-2026
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Downloads counter
11
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Large Language Models (LLMs) are increasingly used by humans for decision-making support. LLMs still exhibit a large ”value-action gap”; a model states that it aligns with specific human values but fails to select consistent actions in situational dilemmas. Prior work has tried to close this gap by using abstract value-descriptive prompting. However, this does not capture the stable, individual character traits that shape real human decisions. Therefore we investigate whether prompting a model with a 4-dimensional virtue profile (courage, justice, temperance, and wisdom) improves value-action alignment compared to an unconditioned baseline. To do so, we generate a dataset containing 616 unique scenarios (56 Schwartz values × 11 social contexts). A total of 40 virtue profiles are tested on this dataset.
Our findings demonstrate that the value-action gap can be partially reduced, but it depends on profile quality. Balanced, moderate-virtue profiles perform best, reducing the mean alignment distance by 20.5% (p < 0.001). Low virtue profiles consistently worsen alignment. Notably, we find that the alignment rate remains stable at around 80.0% for the baseline and balanced profiles. This reveals a behavioral floor effect where underlying alignment training dictates the direction of a choice, while virtue prompting can only adjust its intensity.

Files

Final_research_paper-26.pdf
(pdf | 2.45 Mb)
License info not available