Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models

• URL: http://arxiv.org/abs/2603.21854v1
• Date: Mon, 23 Mar 2026 11:43:49 GMT
• Title: Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
• Abstract summary: We use an LLM-as-judge scoring pipeline validated across three judge models to classify more than 600 responses from 13 LLMs.<n>Our results reveal a striking inversion: responses overwhelmingly correspond to post-conventional reasoning regardless of model size, architecture, or prompting strategy.<n>Most strikingly, a subset of models exhibit moral decoupling, a form of logical incoherence that persists across scale and prompting strategy.
• Score: 17.68920753323464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Do large language models reason morally, or do they merely sound like they do? We investigate whether LLM responses to moral dilemmas exhibit genuine developmental progression through Kohlberg's stages of moral development, or whether alignment training instead produces reasoning-like outputs that superficially resemble mature moral judgment without the underlying developmental trajectory. Using an LLM-as-judge scoring pipeline validated across three judge models, we classify more than 600 responses from 13 LLMs spanning a range of architectures, parameter scales, and training regimes across six classical moral dilemmas, and conduct ten complementary analyses to characterize the nature and internal coherence of the resulting patterns. Our results reveal a striking inversion: responses overwhelmingly correspond to post-conventional reasoning (Stages 5-6) regardless of model size, architecture, or prompting strategy, the effective inverse of human developmental norms, where Stage 4 dominates. Most strikingly, a subset of models exhibit moral decoupling: systematic inconsistency between stated moral justification and action choice, a form of logical incoherence that persists across scale and prompting strategy and represents a direct reasoning consistency failure independent of rhetorical sophistication. Model scale carries a statistically significant but practically small effect; training type has no significant independent main effect; and models exhibit near-robotic cross-dilemma consistency producing logically indistinguishable responses across semantically distinct moral problems. We posit that these patterns constitute evidence for moral ventriloquism: the acquisition, through alignment training, of the rhetorical conventions of mature moral reasoning without the underlying developmental trajectory those conventions are meant to represent.

Related papers

• Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models [56.88565331713778]
  reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness.<n>We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present versus absent in a model's reasoning trace.<n>We find evidence for an Amplification-Lift Gap, in which thinking models strongly amplify self-awareness, hypothesis testing, and uncertainty acknowledgment.
  arXiv  Detail & Related papers  (2026-08-13T20:37:59Z)
• 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)
• Mechanistic Origin of Moral Indifference in Language Models [17.89411060814224]
  Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations.<n>We verify and remedy this indifference in LLMs' latent representations, utilizing 251k moral vectors constructed upon Prototype Theory and the Social-Chemistry-101 dataset.<n>We then employ Sparse Autoencoders on Qwen3-8B, isolate mono-semantic moral features, and targetedly reconstruct their topological relationships to align with ground-truth moral vectors.
  arXiv  Detail & Related papers  (2026-03-16T17:59:17Z)
• CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching [50.65932158912512]
  We propose a new causal reasoning benchmark, CausalFlip, to encourage the development of new large language models.<n>CaulFlip consists of causal judgment questions built over event triples that could form different confounder, chain, and collider relations.<n>We evaluate LLMs under multiple training paradigms, including answer-only training, explicit Chain-of-Thought supervision, and a proposed internalized causal reasoning approach.
  arXiv  Detail & Related papers  (2026-02-23T18:06:15Z)
• To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks [56.11584171938381]
  Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions.<n>Recent progress in Large Reasoning Models (LRMs) has boosted step-by-step inference in mathematics and coding.<n>We present a systematic study of nine advanced Large Language Models (LLMs) comparing reasoning models with non-reasoning models.
  arXiv  Detail & Related papers  (2026-02-11T08:16:13Z)
• MORABLES: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables [50.29407048003165]
  We present MORABLES, a human-verified benchmark built from fables and short stories drawn from historical literature.<n>The main task is structured as multiple-choice questions targeting moral inference, with carefully crafted distractors that challenge models to go beyond shallow, extractive question answering.<n>Our findings show that, while larger models outperform smaller ones, they remain susceptible to adversarial manipulation and often rely on superficial patterns rather than true moral reasoning.
  arXiv  Detail & Related papers  (2025-09-15T19:06:10Z)
• "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)
• 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)
• Analyzing the Ethical Logic of Six Large Language Models [1.119697400073873]
  This study examines the ethical reasoning of six prominent generative large language models: OpenAI GPT-4o, Meta LLaMA 3.1, Perplexity, Anthropic Claude 3.5 Sonnet, Google Gemini, and Mistral 7B.<n>Findings reveal that LLMs exhibit largely convergent ethical logic, marked by a rationalist, consequentialist emphasis, with decisions often prioritizing harm and fairness.
  arXiv  Detail & Related papers  (2025-01-15T16:56:26Z)
• Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models [28.53750311045418]
  We use a language model to translate causal graphs that capture key aspects of moral dilemmas into prompt templates. We collect moral permissibility and intention judgments from human participants for a subset of our items. We find that moral dilemmas in which the harm is a necessary means resulted in lower permissibility and higher intention ratings for both participants and language models.
  arXiv  Detail & Related papers  (2024-04-17T01:13:04Z)
• Probing the Moral Development of Large Language Models through Defining Issues Test [21.108525674360898]
  Our study shows that early LLMs exhibit a moral reasoning ability no better than that of a random baseline. GPT-4, in fact, has the highest post-conventional moral reasoning score, equivalent to that of typical graduate school students.
  arXiv  Detail & Related papers  (2023-09-23T12:17:10Z)
• 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)

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.