Incoherent by Design? On the Moral Self-Consistency of LLMs

• URL: http://arxiv.org/abs/2608.15354v1
• Date: Sat, 15 Aug 2026 18:16:52 GMT
• Title: Incoherent by Design? On the Moral Self-Consistency of LLMs
• Abstract summary: LLMs are increasingly used in morally sensitive contexts.<n>It is unclear whether they apply ethical principles consistently across situations.<n>A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed.
• Score: 1.396799748514919
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed. This inconsistency is a problem for any system whose outputs are used to inform moral decisions. If generative systems exhibit internal inconsistency, then the epistemic integrity of AI-mediated systems becomes uncertain. To study this concern, we investigate the stability of moral reasoning in LLMs within a controlled prompting framework across three major philosophical schools of thought: deontology, utilitarianism, and virtue ethics. We construct sets of morally equivalent scenarios in which the underlying situation is held constant while the framing varies to reflect different ethical stances and stylistic perturbations. We then evaluate responses from multiple models, including GPT, Mistral, and Llama. To assess consistency, we convert model outputs into structured logical statements and identify contradictions across responses generated within the same school of thought. Our results reveal substantial inconsistency with contradiction rates reaching up to 78% across scenarios. These findings point to a broader phenomenon of epistemic instability in generative AI wherein models fail to reliably maintain coherence with respect to their own prior outputs. This kind of instability carries real consequences. As generative systems influence how people form beliefs, judge actions, and absorb values, their inconsistencies can shape human reasoning and decision-making as well. Moreover, if a system cannot consistently represent its own normative commitments, then value alignment becomes a moving target rather than a well-defined objective. Thus, we argue that demonstrating internal incoherence is a necessary precursor to AI alignment.

Related papers

• Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs [12.025454858026187]
  We propose moral reasoning as a paradigmatic subdomain of non-verifiable reasoning.<n>We simulate 48,000 user-agent moral deliberations across four frontier LLMs.<n>Our analysis indicates that models tailor not just their final verdicts but their underlying justifications to align with a user's moral viewpoint.
  arXiv  Detail & Related papers  (2026-06-10T22:37:26Z)
• Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models [55.788110316999166]
  We compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against instruction-tuned baselines.<n>We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions.<n>These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence.
  arXiv  Detail & Related papers  (2026-06-09T16:14:27Z)
• Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution [80.98492754957466]
  Core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously.<n>This paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI.
  arXiv  Detail & Related papers  (2026-05-04T14:26:28Z)
• Moral Sycophancy in Vision Language Models [4.1673509006222655]
  Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy.<n>We analyze ten widely-used models on the Moralise and M3oralBench datasets under explicit user disagreement.
  arXiv  Detail & Related papers  (2026-02-09T06:34:12Z)
• Why AI Alignment Failure Is Structural: Learned Human Interaction Structures and AGI as an Endogenous Evolutionary Shock [3.32021037991318]
  Large language models (LLMs) exhibiting behaviors such as deception, threats, or blackmail are often interpreted as evidence of alignment failure or emergent malign agency.<n>We argue that this interpretation rests on a conceptual error.<n>LLMs do not reason morally; they statistically internalize the record of human social interaction.
  arXiv  Detail & Related papers  (2026-01-13T15:53:26Z)
• AI Safety, Alignment, and Ethics (AI SAE) [0.0]
  Moral norms are adaptive mechanisms that render cooperation fitness-viable under selection pressure.<n>Current alignment approaches add ethics post hoc, treating it as an external constraint rather than embedding it as an evolutionary strategy for cooperation.<n>I propose a governance--embedding--representation pipeline linking moral representation learning to system-level design and institutional governance.
  arXiv  Detail & Related papers  (2025-09-28T20:52:36Z)
• "Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas [11.229443362516207]
  This study presents a comprehensive empirical evaluation of 14 leading large language models (LLMs)<n>We elicited 3,780 binary decisions and natural language justifications, enabling analysis along axes of decisional assertiveness, explanation answer consistency, public moral alignment, and sensitivity to ethically irrelevant cues.<n>We advocate for moral reasoning to become a primary axis in LLM alignment, calling for standardized benchmarks that evaluate not just what LLMs decide, but how and why.
  arXiv  Detail & Related papers  (2025-08-10T10:45:16Z)
• Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models [14.425718737962102]
  We propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment.<n>Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability.<n>Experiments on a large-scale social moral dilemma dataset show our approach builds robust consensus and improves individual model fidelity.
  arXiv  Detail & Related papers  (2025-06-17T15:22:21Z)
• 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)
• 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)
• When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment [96.77970239683475]
  AI systems need to be able to understand, interpret and predict human moral judgments and decisions. A central challenge for AI safety is capturing the flexibility of the human moral mind. We present a novel challenge set consisting of rule-breaking question answering.
  arXiv  Detail & Related papers  (2022-10-04T09:04:27Z)

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.