Exploring the Value-Action gap

language models and cultural-political personas

Bachelor Thesis (2026)
Author(s)

R.W.J. Lakerveld (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

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

A. Homayounirad – 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
Coordinates
51.998778,4.373667
Graduation Date
22-06-2026
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Downloads counter
10
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 (LMs) frequently demonstrate a "value-action gap," explicitly endorsing specific moral values while simultaneously generating contradicting action recommendations in identical scenarios. This gap could be reduced by conditioning LMs with a persona defined by its cultural-political orientation, giving the LM sufficient context to consistently reason about the dilemma.
To analyze this, we introduce a dataset of moral dilemmas alongside a methodology to generate personas based purely on cultural variables of the Inglehart-Welzel Cultural map.
Our experiments reveal that conditioning LMs with these structured profiles generally reduces the value-action gap across all tested architectures. This improvement is most pronounced for internally consistent cultural-political orientations, both for moderate and more radical perspectives. However, language models continue to struggle significantly with internally incongruous personas. These findings underscore a persistent challenge in LM value reasoning.

Files

License info not available