English
Related papers

Related papers: Token-Level Density-Based Uncertainty Quantificati…

200 papers

Statistical models are inherently uncertain. Quantifying or at least upper-bounding their uncertainties is vital for safety-critical systems such as autonomous vehicles. While standard neural networks do not report this information, several…

As large language models (LLMs) continue to evolve, understanding and quantifying the uncertainty in their predictions is critical for enhancing application credibility. However, the existing literature relevant to LLM uncertainty…

Computation and Language · Computer Science 2024-10-22 Hsiu-Yuan Huang , Yutong Yang , Zhaoxi Zhang , Sanwoo Lee , Yunfang Wu

Deep learning-based numerical schemes for solving high-dimensional backward stochastic differential equations (BSDEs) have recently raised plenty of scientific interest. While they enable numerical methods to approximate very…

Numerical Analysis · Mathematics 2023-10-06 Lorenc Kapllani , Long Teng , Matthias Rottmann

Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked tokens at each step. Existing decoding strategies rely on static confidence metrics…

Computation and Language · Computer Science 2026-04-21 Yue Wu , Jian Huang

Uncertainty quantification (UQ) has increasing importance in building robust high-performance and generalizable materials property prediction models. It can also be used in active learning to train better models by focusing on getting new…

Materials Science · Physics 2022-11-14 Daniel Varivoda , Rongzhi Dong , Sadman Sadeed Omee , Jianjun Hu

Uncertainty quantification (UQ) is important to machine learning (ML) force fields to assess the level of confidence during prediction, as ML models are not inherently physical and can therefore yield catastrophically incorrect predictions.…

Chemical Physics · Physics 2022-11-22 Yuge Hu , Joseph Musielewicz , Zachary Ulissi , Andrew J. Medford

Reward models are central to aligning large language models (LLMs) with human preferences. Yet most approaches rely on pointwise reward estimates that overlook the epistemic uncertainty in reward models arising from limited human feedback.…

Machine Learning · Computer Science 2026-03-02 Daniel Yang , Samuel Stante , Florian Redhardt , Lena Libon , Parnian Kassraie , Ido Hakimi , Barna Pásztor , Andreas Krause

Large Language Models (LLMs) have been widely employed in programming language analysis to enhance human productivity. Yet, their reliability can be compromised by various code distribution shifts, leading to inconsistent outputs. While…

Software Engineering · Computer Science 2024-02-12 Yufei Li , Simin Chen , Yanghong Guo , Wei Yang , Yue Dong , Cong Liu

Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. Deploying LLMs for medical question answering necessitates reliable uncertainty estimation (UE)…

Computation and Language · Computer Science 2024-07-12 Jiaxin Wu , Yizhou Yu , Hong-Yu Zhou

Uncertainty quantification (UQ) includes the characterization, integration, and propagation of uncertainties that result from stochastic variations and a lack of knowledge or data in the natural world. Monte Carlo (MC) method is a…

Methodology · Statistics 2020-11-03 Jiaxin Zhang

Uncertainty quantification (UQ) techniques are frequently used to ascertain output variability in systems with parametric uncertainty. Traditional algorithms for UQ are either system-agnostic and slow (such as Monte Carlo) or fast with…

Computation · Statistics 2015-03-19 Tuhin Sahai , Jose Miguel Pasini

Graphical models have demonstrated their exceptional capabilities across numerous applications. However, their performance, confidence, and trustworthiness are often limited by the inherent randomness in data generation and the lack of…

Machine Learning · Computer Science 2026-04-15 Chao Chen , Chenghua Guo , Rui Xu , Jiujiu Chen , Xiangwen Liao , Xi Zhang , Sihong Xie , Hui Xiong , Philip Yu

Deep learning is gaining increasing popularity for spatiotemporal forecasting. However, prior works have mostly focused on point estimates without quantifying the uncertainty of the predictions. In high stakes domains, being able to…

Artificial Intelligence · Computer Science 2021-06-15 Dongxia Wu , Liyao Gao , Xinyue Xiong , Matteo Chinazzi , Alessandro Vespignani , Yi-An Ma , Rose Yu

While Large Language Models (LLMs) demonstrate impressive capabilities, they still struggle with generating factually incorrect content (i.e., hallucinations). A promising approach to mitigate this issue is enabling models to express…

Computation and Language · Computer Science 2025-06-05 Ruihan Yang , Caiqi Zhang , Zhisong Zhang , Xinting Huang , Sen Yang , Nigel Collier , Dong Yu , Deqing Yang

Uncertainty quantification (UQ) is crucial for deploying machine learning models in high-stakes applications, where overconfident predictions can lead to serious consequences. An effective UQ method must balance computational efficiency…

Machine Learning · Computer Science 2026-02-23 Taeseong Yoon , Heeyoung Kim

Diagnostic testing provides a unique setting for studying and developing tools in classification theory. In such contexts, the concept of prevalence, i.e. the number of individuals with a given condition, is fundamental, both as an inherent…

Machine learning in high-stakes domains such as healthcare requires not only strong predictive performance but also reliable uncertainty quantification (UQ) to support human oversight. Multi-label text classification (MLTC) is a central…

Computation and Language · Computer Science 2026-04-17 Raunak Agarwal , Markus Wenzel , Simon Baur , Jonas Zimmer , George Harvey , Jackie Ma

Multi-agent LLM systems, where multiple prompted instances of a language model independently answer questions, are increasingly used for complex reasoning tasks. However, existing methods for quantifying the uncertainty of their collective…

Computation and Language · Computer Science 2026-03-24 Bo Jiang

In recent years, large-scale language models (LLMs) have gained attention for their impressive text generation capabilities. However, these models often face the challenge of "hallucination," which undermines their reliability. In this…

Computation and Language · Computer Science 2023-10-10 Yuchen Yang , Houqiang Li , Yanfeng Wang , Yu Wang

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

Computation and Language · Computer Science 2024-12-11 Min Zeng , Caiquan Liu , Shiqi Zhang , Li Xie , Chen Sang , Xiaoxin Chen