Enhancing the moral alignment of Large Language Models (LLMs) is a critical challenge in AI safety. Current alignment techniques often act as superficial guardrails, leaving the intrinsic moral representations of LLMs largely untouched. In this paper, we bridge this gap by leveraging Moral Foundations Theory (MFT) to map and manipulate the fine-grained moral landscape of LLMs. Through cross-lingual linear probing, we validate the shared nature of moral representations in middle layers and uncover a shared yet different moral subspace between English and Chinese. Building upon this, we extract steerable Moral Vectors and successfully validate their efficacy at both internal and behavioral levels. Leveraging the high generalizability of morality, we propose Adaptive Moral Fusion (AMF), a dynamic inference-time intervention that synergizes probe detection with vector injection to tackle the safety-helpfulness trade-off. Empirical results confirm that our approach acts as a targeted intrinsic defense, effectively reducing incorrect refusals on benign queries while minimizing jailbreak success rates compared to standard baselines.

翻译：提升大语言模型（LLMs）的道德对齐是人工智能安全领域的一个关键挑战。当前的对齐技术通常仅作为表面防护栏，并未触及LLMs内在的道德表征。本文通过利用道德基础理论（MFT）来映射和操控LLMs细粒度的道德图景，以弥合这一差距。通过跨语言线性探测，我们验证了中间层道德表征的共享性质，并揭示了英语与中文之间共享但存在差异的道德子空间。在此基础上，我们提取了可操控的道德向量，并成功在内部和行为层面验证了其有效性。利用道德的高泛化性，我们提出了自适应道德融合（AMF），这是一种动态推理时干预方法，它将探测检测与向量注入相结合，以应对安全性与有用性之间的权衡。实证结果证实，我们的方法作为一种有针对性的内在防御机制，与标准基线相比，能有效减少对良性查询的错误拒绝，同时最大程度地降低越狱成功率。