Uncertainty Propagation in LLM-Based Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913062781452288 |
|---|---|
| author | Xia, Boming Zhu, Liming Gao, Erdun Lu, Qinghua Xue, Minhui Sejdinovic, Dino |
| author_facet | Xia, Boming Zhu, Liming Gao, Erdun Lu, Qinghua Xue, Minhui Sejdinovic, Dino |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23505 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uncertainty Propagation in LLM-Based Systems Xia, Boming Zhu, Liming Gao, Erdun Lu, Qinghua Xue, Minhui Sejdinovic, Dino Software Engineering Artificial Intelligence 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. |
| title | Uncertainty Propagation in LLM-Based Systems |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2604.23505 |