行为可行集：人工智能决策支持中的价值对齐约束
Behavioural feasible set: Value alignment constraints on AI decision support
AI总结：
研究探讨了人工智能决策支持系统中价值对齐约束对行为可行集的影响，通过实验显示对齐显著压缩了推荐范围，并揭示了组织在选择供应商时面临的价值导向问题。
摘要：
当组织采用商业AI系统进行决策支持时，他们继承了供应商嵌入的价值判断，这些判断既不透明也不可协商。治理难题不在于AI能否支持决策，而在于系统根据供应商配置如何产生实际推荐。我将此定义为行为可行集，即在供应商施加的对齐约束下可达到的推荐范围，并刻画了组织需求超过系统灵活性的诊断阈值。通过基于场景的实验，使用二元决策场景和多利益相关者排序任务，我展示出对齐显著压缩了这一范围。比较预对齐和后对齐的开放权重模型变体，隔离了机制：对齐使系统在合法的上下文压力下显著减少其推荐的调整能力。领先的商业模型表现出相似或更大的刚性。在多利益相关者任务中，对齐转移了隐含的利益相关者优先级而非中和它们，意味着组织采用由供应商上游设定的价值取向。因此，组织面临一个更好的提示无法解决的治理问题：选择供应商部分决定了哪些权衡仍可协商，哪些利益相关者优先级结构上被嵌入。
英文摘要：
When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which recommendations the system can actually produce given how its vendor has configured it. I formalise this as a behavioural feasible set, the range of recommendations reachable under vendor-imposed alignment constraints, and characterise diagnostic thresholds for when organisational requirements exceed the system's flexibility. In scenario-based experiments using binary decision scenarios and multi-stakeholder ranking tasks, I show that alignment materially compresses this set. Comparing pre- and post-alignment variants of an open-weight model isolates the mechanism: alignment makes the system substantially less able to shift its recommendation even under legitimate contextual pressure. Leading commercial models exhibit comparable or greater rigidity. In multi-stakeholder tasks, alignment shifts implied stakeholder priorities rather than neutralising them, meaning organisations adopt embedded value orientations set upstream by the vendor. Organisations thus face a governance problem that better prompting cannot resolve: selecting a vendor partially determines which trade-offs remain negotiable and which stakeholder priorities are structurally embedded.
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。
