推理还是修辞？对大型语言模型中道德推理解释的实证分析
Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
AI总结：
研究通过分析LSTM对道德困境的回应，探讨其是否具备道德发展阶段的真正进展，发现其表现出后常规推理，且存在道德解耦现象，揭示了对成熟道德推理的修辞模仿。
摘要：
大型语言模型是否进行道德推理，还是仅仅听起来像在推理？我们研究LLM对道德困境的回应是否表现出科尔伯格道德发展阶段的真实发展轨迹，或是否通过对齐训练产生类似成熟道德判断的推理样输出。使用经过三个判断模型验证的LLM-as-judge评分流程，我们对13个LLM的600多个回应进行了分类，涵盖不同架构、参数规模和训练方法的六个经典道德困境，并进行了十种互补分析，以描述所获模式的性质和内部一致性。我们的结果揭示了惊人的反转：无论模型大小、架构或提示策略，回应普遍对应于后常规推理（第5-6阶段），这与人类发展规范的逆向相反，其中第4阶段占主导地位。最引人注目的是，部分模型表现出道德解耦：陈述的道德辩护与行动选择之间存在系统性不一致，这是一种持续存在的逻辑不一致，无论规模和提示策略如何，均代表了独立于修辞复杂性的推理一致性失败。模型规模具有统计上显著但实际影响小的效果；训练类型无显著独立主效应；且模型表现出近机器的跨困境一致性，产生在语义上不同的道德问题中逻辑上无法区分的回应。我们提出这些模式构成了道德拟人化的证据：通过对齐训练获得成熟道德推理的修辞惯例，而没有这些惯例所代表的底层发展轨迹。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
