Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.08634 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909988884054016 |
|---|---|
| author | Yuan, Chenchen Ma, Bolei Zhang, Zheyu Prenkaj, Bardh Kreuter, Frauke Kasneci, Gjergji |
| author_facet | Yuan, Chenchen Ma, Bolei Zhang, Zheyu Prenkaj, Bardh Kreuter, Frauke Kasneci, Gjergji |
| contents | 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 such conditioning induces pronounced, value-specific shifts in models' political coordinates. We further notice that these effects are systematically modulated by role framing and model scale, and are robust across alternative assessment instruments instantiating the same moral value. This highlights that effective alignment requires anchoring political assessments within the context of broader social values including morality, paving the way for more socially grounded alignment techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08634 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs Yuan, Chenchen Ma, Bolei Zhang, Zheyu Prenkaj, Bardh Kreuter, Frauke Kasneci, Gjergji Computation and Language Artificial Intelligence 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 such conditioning induces pronounced, value-specific shifts in models' political coordinates. We further notice that these effects are systematically modulated by role framing and model scale, and are robust across alternative assessment instruments instantiating the same moral value. This highlights that effective alignment requires anchoring political assessments within the context of broader social values including morality, paving the way for more socially grounded alignment techniques. |
| title | Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.08634 |