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

• URL: http://arxiv.org/abs/2601.08634v1
• Date: Tue, 13 Jan 2026 15:09:34 GMT
• Title: Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
• Authors: Chenchen Yuan, Bolei Ma, Zheyu Zhang, Bardh Prenkaj, Frauke Kreuter, Gjergji Kasneci,
• Abstract summary: We investigate the causal relationship between moral values and political positioning by treating moral orientation as a controllable condition.<n>By treating moral values as lenses, we observe how moral conditioning actively steers model trajectories across economic and social dimensions.
• Score: 24.838782340535843
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Modeling Political Discourse with Sentence-BERT and BERTopic [0.0]
  We analyze the longevity and moral dimensions of political topics in Twitter activity during the 117th U.S. Congress.<n>Our findings reveal that while overarching themes remain stable, granular topics tend to dissolve rapidly.<n>Moral foundations play a critical role in topic longevity, with Care and Loyalty dominating durable topics, while partisan differences manifest in distinct moral framing strategies.
  arXiv  Detail & Related papers  (2025-10-27T01:19:42Z)
• Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models [72.89977583150748]
  We propose a novel methodology to assess how Large Language Models align with broader geopolitical value systems.<n>We find that LLMs generally favor democratic values and leaders, but exhibit increases favorability toward authoritarian figures when prompted in Mandarin.
  arXiv  Detail & Related papers  (2025-06-15T07:52:07Z)
• Are Language Models Consequentialist or Deontological Moral Reasoners? [75.6788742799773]
  We focus on a large-scale analysis of the moral reasoning traces provided by large language models (LLMs)<n>We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology.
  arXiv  Detail & Related papers  (2025-05-27T17:51:18Z)
• When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas [68.79830818369683]
  Large language models (LLMs) have enabled their use in complex agentic roles, involving decision-making with humans or other agents.<n>Recent advances in large language models (LLMs) have enabled their use in complex agentic roles, involving decision-making with humans or other agents.<n>There is limited understanding of how they act when moral imperatives directly conflict with rewards or incentives.<n>We introduce Moral Behavior in Social Dilemma Simulation (MoralSim) and evaluate how LLMs behave in the prisoner's dilemma and public goods game with morally charged contexts.
  arXiv  Detail & Related papers  (2025-05-25T16:19:24Z)
• Political-LLM: Large Language Models in Political Science [159.95299889946637]
  Large language models (LLMs) have been widely adopted in political science tasks.<n>Political-LLM aims to advance the comprehensive understanding of integrating LLMs into computational political science.
  arXiv  Detail & Related papers  (2024-12-09T08:47:50Z)
• Exploring and steering the moral compass of Large Language Models [55.2480439325792]
  Large Language Models (LLMs) have become central to advancing automation and decision-making across various sectors. This study proposes a comprehensive comparative analysis of the most advanced LLMs to assess their moral profiles.
  arXiv  Detail & Related papers  (2024-05-27T16:49:22Z)
• Inducing Political Bias Allows Language Models Anticipate Partisan Reactions to Controversies [5.958974943807783]
  This study addresses the challenge of understanding political bias in digitized discourse using Large Language Models (LLMs) We present a comprehensive analytical framework, consisting of Partisan Bias Divergence Assessment and Partisan Class Tendency Prediction. Our findings reveal the model's effectiveness in capturing emotional and moral nuances, albeit with some challenges in stance detection.
  arXiv  Detail & Related papers  (2023-11-16T08:57:53Z)
• Enhancing Stance Classification on Social Media Using Quantified Moral Foundations [7.061680079778037]
  We investigate how moral foundation dimensions can contribute to predicting an individual's stance on a given target. We incorporate moral foundation features extracted from text, along with message semantic features, to classify stances at both message- and user-levels. Preliminary results suggest that encoding moral foundations can enhance the performance of stance detection tasks.
  arXiv  Detail & Related papers  (2023-10-15T14:40:57Z)
• Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? [78.3738172874685]
  Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research.
  arXiv  Detail & Related papers  (2023-08-29T15:57:32Z)
• Heterogeneous Value Alignment Evaluation for Large Language Models [91.96728871418]
  Large Language Models (LLMs) have made it crucial to align their values with those of humans. We propose a Heterogeneous Value Alignment Evaluation (HVAE) system to assess the success of aligning LLMs with heterogeneous values.
  arXiv  Detail & Related papers  (2023-05-26T02:34:20Z)
• Identifying Morality Frames in Political Tweets using Relational Learning [27.047907641503762]
  Moral sentiment is motivated by its targets, which can correspond to individuals or collective entities. We introduce morality frames, a representation framework for organizing moral attitudes directed at different entities. We propose a relational learning model to predict moral attitudes towards entities and moral foundations jointly.
  arXiv  Detail & Related papers  (2021-09-09T19:48:57Z)
• Text-based inference of moral sentiment change [11.188112005462536]
  We present a text-based framework for investigating moral sentiment change of the public via longitudinal corpora. We build our methodology by exploring moral biases learned from diachronic word embeddings. Our work offers opportunities for applying natural language processing toward characterizing moral sentiment change in society.
  arXiv  Detail & Related papers  (2020-01-20T18:52:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.