Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
Chenchen Yuan, Bolei Ma, Zheyu Zhang, Bardh Prenkaj, Frauke Kreuter, Gjergji Kasneci

TL;DR
This paper explores how conditioning large language models on specific moral values can causally influence their political orientations, revealing value-specific shifts and implications for socially grounded alignment.
Contribution
It introduces a method to steer LLMs' political positions via moral conditioning, linking moral intuitions to ideological biases systematically.
Findings
Moral conditioning causes significant shifts in political coordinates.
Effects are influenced by role framing and model scale.
Robust across different moral assessment tools.
Abstract
While recent research has systematically documented political orientation in large language models (LLMs), existing evaluations rely primarily on direct probing or demographic persona engineering to surface ideological biases. In social psychology, however, political ideology is also understood as a downstream consequence of fundamental moral intuitions. In this work, we investigate the causal relationship between moral values and political positioning by treating moral orientation as a controllable condition. Rather than simply assigning a demographic persona, we condition models to endorse or reject specific moral values and evaluate the resulting shifts on their political orientations, using the Political Compass Test. By treating moral values as lenses, we observe how moral conditioning actively steers model trajectories across economic and social dimensions. Our findings show that…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputational and Text Analysis Methods · Social Power and Status Dynamics · Topic Modeling
