Uncertainty Propagation in LLM-Based Systems
For researchers and engineers building compound LLM systems, this work provides a conceptual framework to understand and manage uncertainty propagation, though it is primarily a taxonomy and problem framing without empirical validation.
The paper develops a systems-level account of uncertainty propagation in LLM-based systems, introducing a taxonomy spanning intra-model, system-level, and socio-technical mechanisms, and identifies five open research challenges.
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.