LLM在确定性流程中的非确定性：用于约束非确定性传播的受控变化空间
LLM Non-Determinism in Deterministic Processes: A Controlled Variation Space for Constraining the Propagation of Non-Determinism
- Findustrial GmbH（Findustrial有限公司）
- Munich University of Applied Sciences（慕尼黑应用科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对LLM在确定性软件开发流程中引入非确定性的问题，提出受控非确定性方法，通过确定性包络和退出检查约束变化，确保流程状态可靠可控。
AI中文摘要：
大型语言模型越来越多地被用于依赖定义状态、规则和审批的软件开发流程中。这造成了LLM的灵活性与对可靠且可追踪流程状态的需求之间的张力。我们引入了受控非确定性（Controlled Non-Determinism），这是一种面向流程的方法，允许变化存在，但不让其直接决定权威流程状态。我们将基于LLM的处理置于一个受控变化空间内，该空间由确定性包络（Deterministic Envelope）界定。在执行之前，我们定义结果的流程相关属性和退出条件。我们还记录任务配置。这些元素在执行期间保持不变。在变化空间的末端，退出检查确定结果是否满足预定义条件，并可能成为下一个权威状态。不同的运行可能产生不同的可接受结果，而向权威状态的转换仍然受到控制。我们以受监管的软件开发为例说明该方法，并推导出基于LLM的变更的设计指南，这些变更的结果在成为权威软件状态的一部分之前可以被检查。
英文摘要：
Large Language Models are increasingly used in software development processes that rely on defined states, rules, and approvals. This creates a tension between the flexibility of LLMs and the need for reliable and traceable process states. We introduce Controlled Non-Determinism, a process-oriented approach that allows variation without letting it directly determine the authoritative process state. We place LLM-based processing within a controlled variation space that is bounded by a Deterministic Envelope. Before execution, we define the process-relevant properties of the result and the exit conditions. We also record the task configuration. These elements remain fixed during execution. At the end of the variation space, an exit check determines whether the result satisfies the predefined conditions and may become the next authoritative state. Different runs may produce different admissible results while the transition to an authoritative state remains controlled. We illustrate the approach with regulated software development and derive design guidelines for LLM-based changes whose results can be checked before they become part of the authoritative software state.
