对LLM对齐中的困境和冲突是否可解？一种优先图的视角
Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph
AI总结：
本文通过优先图模型分析LLM在不同场景中的冲突与困境，揭示了统一稳定对齐的挑战及优先黑客的潜在风险，并提出运行时验证机制以提升鲁棒性。
摘要：
随着大型语言模型（LLMs）变得更强大和自主，它们在许多场景中面临越来越多的冲突和困境。我们首先总结并分类这些多样化的冲突。然后，我们将LLM的偏好建模为优先图，其中指令和价值观是节点，边代表由模型输出分布决定的上下文特定优先级。该图揭示了统一稳定LLM对齐非常具有挑战性，因为该图既不静态也不一定在不同上下文中保持一致。此外，它还揭示了潜在的漏洞：优先黑客，即对手可以制造欺骗性上下文来操纵图并绕过安全对齐。为应对这一问题，我们提出了一种运行时验证机制，使LLM能够查询外部来源以确定其上下文并抵御操纵。尽管这种方法增强了鲁棒性，我们也认识到许多伦理和价值困境是哲学上不可还原的，这构成了AI对齐未来长期和开放的挑战。
英文摘要：
As Large Language Models (LLMs) become more powerful and autonomous, they increasingly face conflicts and dilemmas in many scenarios. We first summarize and taxonomize these diverse conflicts. Then, we model the LLM's preferences to make different choices as a priority graph, where instructions and values are nodes, and the edges represent context-specific priorities determined by the model's output distribution. This graph reveals that a unified stable LLM alignment is very challenging, because the graph is neither static nor necessarily consistent in different contexts. Besides, it also reveals a potential vulnerability: priority hacking, where adversaries can craft deceptive contexts to manipulate the graph and bypass safety alignments. To counter this, we propose a runtime verification mechanism, enabling LLMs to query external sources to ground their context and resist manipulation. While this approach enhances robustness, we also acknowledge that many ethical and value dilemmas are philosophically irreducible, posing a long-term, open challenge for the future of AI alignment.
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。
