Research
Uncertainty Propagation in LLM-Based Systems
arXiv:2604.23505v1 Announce Type: cross Abstract: Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are comp
arXiv:2604.23505v1 Announce Type: cross Abstract: 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.
Related
- TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
- Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations
- Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
- Hallucination as output-boundary misclassification: a composite abstention architecture for language models
Source: arXiv cs.AI | 2026-04-28