Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs

2026-01-13

AI Summary

This study addresses a critical gap in evaluating political orientations of large language models (LLMs), which has predominantly relied on direct questioning or demographic role-playing, thereby overlooking the causal influence of moral intuitions on political ideology. For the first time, this work treats moral values as a controllable “lens,” employing morality-conditioned prompts to steer LLMs toward specific moral stances. By integrating political compass tests with alternative moral assessment instruments, the authors systematically examine shifts in models’ socio-economic political coordinates across multiple scales. Experimental results demonstrate that moral conditioning robustly and significantly modulates LLMs’ political leanings, revealing the foundational role of moral intuitions in shaping political positions. Furthermore, the study confirms that both role-based framing and model scale moderate this effect, underscoring the interplay between moral foundations and contextual factors in ideological expression.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Morality & Value-based AI
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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 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.

Problem

• moral values
• political ideology
• large language models
• ideological bias
• moral conditioning

Innovation

• moral conditioning
• political alignment
• large language models
• ideological positioning
• value-based steering