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.

翻译：尽管近期研究已系统性地记录了大语言模型（LLM）中的政治倾向，现有评估主要依赖直接探测或人口统计角色工程来揭示意识形态偏见。然而在社会心理学中，政治意识形态也被理解为基本道德直觉的下游产物。本研究通过将道德取向作为可控条件，探究道德价值观与政治定位之间的因果关系。我们并非简单分配人口统计角色，而是通过让模型认可或拒绝特定道德价值观，并利用政治指南针测试评估其政治取向的相应偏移。通过将道德价值观视为透镜，我们观察到道德条件化如何主动引导模型在经济与社会维度上的轨迹变化。研究结果表明，此类条件化会引发模型政治坐标出现显著且具有价值特异性的偏移。我们进一步发现这些效应受到角色框架和模型规模的系统性调节，并在实例化相同道德价值的替代评估工具中保持稳健性。这凸显出有效的对齐需要将政治评估锚定在包括道德在内的更广泛社会价值语境中，从而为更具社会根基的对齐技术开辟道路。