Exploring the Value-Action gap
language models and cultural-political personas
R.W.J. Lakerveld (TU Delft - Electrical Engineering, Mathematics and Computer Science)
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)
More Info
expand_more
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.