Uncertainty Quantification (UQ) is the mathematical study of how uncertainty in model inputs propagates to outputs. It provides methods for estimating confidence intervals, sensitivity, and robustness in computational predictions. UQ is vital for scientific computing, engineering design, and AI safety. Techniques include Monte Carlo simulation, Bayesian inference, and stochastic modeling. Reliable UQ enhances decision-making in systems where precision and trust are essential.
Distributed fiber-optic sensing combined with machine learning enables continuous monitoring of telecom infrastructure. We employ generative modeling for event classification, supporting semi supervised learning, uncertainty calibration, and noise resilience. Our approach offers a scalable, data-efficient solution for real-world deployment in complex environments.
Our researcher Xujiang Zhao will present “Uncertainty Quantification and Reasoning for Reliable AI” at Brigham Young University on Thursday, Sept. 25 at 11 a.m. in TMCB 1170. The seminar explores how statistical modeling and reasoning frameworks can strengthen trustworthy AI, making systems more robust and transparent in high-stakes applications like healthcare and autonomous systems. Attendees will gain insights into how uncertainty quantification is shaping the next generation of responsible AI.
Large language models (LLMs) integrated into multi-step agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multi-step decision-making process and the dynamic interactions between agents and their environments. To address these limitations, we propose SAUP (Situation Awareness Uncertainty Propagation), a novel framework that propagates uncertainty through each step of an LLM-based agent’s reasoning process. SAUP incorporates situational awareness by assigning situational weights to each step’s uncertainty during the propagation. Our method, compatible with various one-step uncertainty estimation techniques, provides a comprehensive and accurate uncertainty measure. Extensive experiments on benchmark datasets demonstrate that SAUP significantly outperforms existing state-of-the-art methods, achieving up to 20% improvement in AUROC.
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLMs response, such as hallucination, have also been actively discussed. Existing works have been devoted to quantifying the uncertainty in LLMs response, but they often overlook the complex nature of LLMs and the uniqueness of in-context learning. In this work, we delve into the predictive uncertainty of LLMs associated with in-context learning, highlighting that such uncertainties may stem from both the provided demonstrations (aleatoric uncertainty) and ambiguities tied to the models configurations (epistemic uncertainty). We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion. Extensive experiments are conducted to demonstrate the effectiveness of the decomposition. The code and data are available at: https://github.com/lingchen0331/UQ_ICL.