概率的道德：LLM中隐含的道德偏见如何塑造人机共生的未来
The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
AI总结：
本文通过定量实验研究了六个LLM在18个困境中的道德偏好，发现模型普遍偏好关怀与美德而惩罚自由意志主义，并强调可解释性与文化意识对实现人机共生的重要性。
摘要：
人工智能（AI）的快速发展引发了关于如何将机器决策与人类道德价值观对齐的紧迫问题。本文探讨了领先的AI系统如何优先考虑道德结果，以及这揭示了人机共生的哪些前景。我们解决了两个核心问题：(1) 当面临困境时，最先进的大型语言模型（LLM）隐含地偏好哪些道德价值观？(2) 模型架构、文化起源和可解释性的差异如何影响这些道德偏好？为了探索这些问题，我们对六个LLM进行了定量实验，对代表五种道德框架的18个困境的结果进行了排名和评分。我们的发现揭示了惊人一致的价值偏见。在所有模型中，关怀和美德价值的结果被评为最具道德，而自由意志主义的选择则持续受到惩罚。具备推理能力的模型对上下文表现出更高的敏感性并提供了更丰富的解释，而非推理模型则产生了更统一但不透明的判断。本研究做出了三项贡献：(i) 在经验上，它对具有文化差异的LLM的道德推理进行了大规模比较；(ii) 在理论上，它将概率模型行为与潜在的价值编码联系起来；(iii) 在实践上，它强调了将可解释性和文化意识作为关键设计原则的必要性，以引导AI走向透明、对齐且共生的未来。
英文摘要：
Artificial intelligence (AI) is advancing at a pace that raises urgent questions about how to align machine decision-making with human moral values. This working paper investigates how leading AI systems prioritize moral outcomes and what this reveals about the prospects for human-AI symbiosis. We address two central questions: (1) What moral values do state-of-the-art large language models (LLMs) implicitly favour when confronted with dilemmas? (2) How do differences in model architecture, cultural origin, and explainability affect these moral preferences? To explore these questions, we conduct a quantitative experiment with six LLMs, ranking and scoring outcomes across 18 dilemmas representing five moral frameworks. Our findings uncover strikingly consistent value biases. Across all models, Care and Virtue values outcomes were rated most moral, while libertarian choices were consistently penalized. Reasoning-enabled models exhibited greater sensitivity to context and provided richer explanations, whereas non-reasoning models produced more uniform but opaque judgments. This research makes three contributions: (i) Empirically, it delivers a large-scale comparison of moral reasoning across culturally distinct LLMs; (ii) Theoretically, it links probabilistic model behaviour with underlying value encodings; (iii) Practically, it highlights the need for explainability and cultural awareness as critical design principles to guide AI toward a transparent, aligned, and symbiotic future.
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。
