arXiv最新论文，在推理时动态引导指令层次结构，有效提升大模型对复杂指令的遵循能力。
arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inp…
多语言LLM中指令层次遵从性因语言而异，揭示语言对模型安全对齐的影响。
arXiv:2607.23545v1 Announce Type: new Abstract: Instruction hierarchy (IH) requires models to prioritize instructions by source, ensuring that higher-…
用重力加权偏好优化让大模型精准服从多级指令层次，提升对齐能力
arXiv:2606.10860v1 Announce Type: cross Abstract: Production LLMs receive instructions from sources with very different levels of trust, yet attend to…