paper-with-me

홈 › Papers

Uncertainty Propagation in LLM-Based Systems

2026-04-26 · Boming Xia, Liming Zhu, Erdun Gao, Qinghua Lu, Minhui Xue, Dino Sejdinovic arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.23505

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Risks of uncertainty propagation in Al-augmented security pipelines

2024-07-14 · Emanuele Mezzi, Aurora Papotti, Fabio Massacci, Katja Tuma

The use of AI technologies is percolating into the secure development of software-based systems, with an increasing trend of composing AI-based subsystems (with uncertain levels of performance) into automated pipelines. …

Uncertainty Propagation through Trained Deep Neural Networks Using Factor Graphs

2023-12-10 · Angel Daruna, Yunye Gong, Abhinav Rajvanshi, Han-Pang Chiu 외

Predictive uncertainty estimation remains a challenging problem precluding the use of deep neural networks as subsystems within safety-critical applications. Aleatoric uncertainty is a component of predictive uncertainty…

PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems

2026-08-22 · Yaokun Liu, Yifan Liu, Daniel Yue Zhang, Ruichen Yao 외 arxiv

LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond isolated agent failures. For instance, err…

Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components

2023-01-12 · Fabio Arnez, Huascar Espinoza, Ansgar Radermacher, François Terrier

As autonomous systems increasingly rely on Deep Neural Networks (DNN) to implement the navigation pipeline functions, uncertainty estimation methods have become paramount for estimating confidence in DNN predictions. Bay…

Deep Learning

Uncertainty Propagation in the Fast Fourier Transform

2025-04-14 · Luca Schmid, Charlotte Muth, Laurent Schmalen

We address the problem of uncertainty propagation in the discrete Fourier transform by modeling the fast Fourier transform as a factor graph. Building on this representation, we propose an efficient framework for approxi…

Bayesian Inference