研究大模型系统中不确定性如何跨环节传播，揭示其累积风险
Uncertainty Propagation in LLM-Based Systems
- 构建系统级不确定性传播框架，覆盖模型内、系统间与人机协作三类机制
- 提出P1/P2/P3三级传播分类法，分析误差如何在流程中层层放大
- 适合关注大模型可靠性与安全的工程师及研究人员
大语言模型（LLM）系统中的不确定性常被局限于单个输出层面研究，但实际部署的应用是复杂的复合系统，不确定性在模型内部、工作流阶段、组件边界、持久状态以及人或组织流程中不断传递与重用。若缺乏对不确定性跨边界传播的系统性处理，早期错误可能以难以察觉和控制的方式持续累积。本文提出一种系统级的不确定性传播分析框架，引入概念性范式以刻画传播的不确定性信号，构建涵盖模型内（P1）、系统级（P2）和人-技术交互（P3）的分类体系，整合跨领域的工程洞见，并识别出五个开放性研究挑战。
原文摘要 · Abstract (English)
Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are compound systems in which uncertainty is transformed and reused across model internals, workflow stages, component boundaries, persistent state, and human or organisational processes. Without principled treatment of how uncertainty is carried and reused across these boundaries, early errors can propagate and compound in ways that are difficult to detect and govern. This paper develops a systems-level account of uncertainty propagation. It introduces a conceptual framing for characterising propagated uncertainty signals, presents a structured taxonomy spanning intra-model (P1), system-level (P2), and socio-technical (P3) propagation mechanisms, synthesises cross-cutting engineering insights, and identifies five open research challenges.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。