Betül Şenyayla¹, Aytuğ Onan^2,*

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.081260 - 23 July 2026

Abstract Large Language Models (LLMs) have become a cornerstone of modern natural language processing, achieving strong performance across diverse tasks. Despite these advances, their tendency to generate hallucinated or factually unsupported content remains a critical challenge for reliable deployment. Existing evaluation approaches predominantly rely on single-task settings and aggregate performance metrics, implicitly assuming that hallucination behavior is uniform across tasks. However, this assumption is fundamentally flawed, as hallucination characteristics vary significantly depending on task formulation, linguistic context, and evaluation criteria. To address these limitations, this paper proposes HalluBench, a task-aware multi-LLM benchmarking framework designed for systematic… More >

Yunlong Teng¹, Ying Liu², Jianhong Liang¹, Jinshang Luo^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.3, 2026, DOI:10.32604/cmes.2026.082594 - 30 June 2026

Abstract Over the past decades, surrogate model-aided reliability analysis approaches grounded in active learning have undergone extensive development. However, Gaussian process models like Kriging suffer from severe computational burdens when handling high-dimensional problems or large samples. Conversely, machine learning algorithms such as extreme learning machines exhibit high computational efficiency but lack variance output and stability, making them difficult to employ for adaptive active learning strategies. To address these limitations, this study proposes a population Monte Carlo method based on an adaptive closed neuron extreme learning machine. First, a closed neuron strategy uses a consistency metric to… More >

Shuoshuo Shen^1,2, Jin Cheng^1,2,*, Zhenyu Liu², Jianrong Tan^1,2

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.2, pp. 1-2, 2025, DOI:10.32604/icces.2025.011752

Abstract Motion stability assessment of industrial robots subject to complex dynamic properties and multi-source uncertainties in open environments registers an important yet challenging task [1–5]. To tackle this task, this study proposes a new reliability-based motion stability analysis method for industrial robots, which incorporates the moment-based method and Bayesian inference-guided probabilistic model updating strategy. To start with, the comprehensive motion system model of industrial robots is established by integrating the control, drive, and multi-body motion models. The reliability-based stability model of industrial robots is presented considering the uncertainty of parameters. Subsequently, the fractional exponential moments are… More >

Baojun Qin^1,2, Hong Jiang^1,2,3, Wei Zhang⁴, Xiang Liu^4,*

Structural Durability & Health Monitoring, Vol.19, No.5, pp. 1203-1220, 2025, DOI:10.32604/sdhm.2025.063813 - 05 September 2025

Abstract The utilization of high-strength steel bars (HSSB) within concrete structures demonstrates significant advantages in material conservation and mechanical performance enhancement. Nevertheless, existing design codes exhibit limitations in addressing the distinct statistical characteristics of HSSB, particularly regarding strength design parameters. For instance, GB50010-2010 fails to specify design strength values for reinforcement exceeding 600 MPa, creating technical barriers for advancing HSSB implementation. This study systematically investigates the reliability of eccentric compression concrete columns reinforced with 600 MPa-grade HSSB through high-order moment method analysis. Material partial factors were calibrated against target reliability indices prescribed by GB50068-2018, incorporating critical More >

Yunhan Ling¹, Huajun Peng², Yiqing Shi^1,*, Chao Xu¹, Jingzhen Yan¹, Jingjing Wang¹, Hui Ma^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.1, pp. 767-808, 2025, DOI:10.32604/cmes.2025.061763 - 11 April 2025

Abstract The traditional first-order reliability method (FORM) often encounters challenges with non-convergence of results or excessive calculation when analyzing complex engineering problems. To improve the global convergence speed of structural reliability analysis, an improved coati optimization algorithm (COA) is proposed in this paper. In this study, the social learning strategy is used to improve the coati optimization algorithm (SL-COA), which improves the convergence speed and robustness of the new heuristic optimization algorithm. Then, the SL-COA is compared with the latest heuristic optimization algorithms such as the original COA, whale optimization algorithm (WOA), and osprey optimization algorithm… More >

Xinxin Yue¹, Jian Zhang^2,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.29, No.4, pp. 1-2, 2024, DOI:10.32604/icces.2024.011344

Abstract The "curse of dimensionality" faced by high-dimensional complex engineering problems can be tackled by a set of quantitative model evaluation and analysis tools named high-dimensional model representation (HDMR) [1,2], which has attracted much attention from researchers in various fields, such as global sensitivity analysis (GSA) [3], structural reliability analysis (SRA) [4], CFD uncertainty quantification [5] and so on [6]. In this paper, a new method for uncertainty quantification is proposed. Firstly, PCE-HDMR for SRA is developed by taking advantage of the accuracy and efficiency of PCE-HDMR for modeling high-dimensional problems [7]. Secondly, the formulas for… More >

Zibin Mao¹, Qinghai Zhao^1,2,*, Liang Zhang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 757-792, 2024, DOI:10.32604/cmes.2024.048016 - 16 April 2024

Abstract This paper proposes a multi-material topology optimization method based on the hybrid reliability of the probability-ellipsoid model with stress constraint for the stochastic uncertainty and epistemic uncertainty of mechanical loads in optimization design. The probabilistic model is combined with the ellipsoidal model to describe the uncertainty of mechanical loads. The topology optimization formula is combined with the ordered solid isotropic material with penalization (ordered-SIMP) multi-material interpolation model. The stresses of all elements are integrated into a global stress measurement that approximates the maximum stress using the normalized p-norm function. Furthermore, the sequential optimization and reliability assessment… More >

Qi Zhang^1,2,4,5, Zhixin Chen³, Yang Wu^4,*, Guoqi Xiang², Guang Wen¹, Xuegang Zhang², Yongchun Xie², Guangchun Yang²

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 593-619, 2024, DOI:10.32604/cmes.2023.046319 - 16 April 2024

Abstract Although there is currently no unified standard theoretical formula for calculating the contact stress of cylindrical gears with a circular arc tooth trace (referred to as CATT gear), a mathematical model for determining the contact stress of CATT gear is essential for studying how parameters affect its contact stress and building the contact stress limit state equation for contact stress reliability analysis. In this study, a mathematical relationship between design parameters and contact stress is formulated using the Kriging Metamodel. To enhance the model’s accuracy, we propose a new hybrid algorithm that merges the genetic… More >

Debiao Meng^1,2,*, Yipeng Guo^1,2, Yihe Xu³, Shiyuan Yang^1,2,*, Yongqiang Guo⁴, Lidong Pan⁴, Xinkai Guo²

CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.3, pp. 2329-2359, 2024, DOI:10.32604/cmes.2024.047507 - 11 March 2024

Abstract The escalating need for reliability analysis (RA) and reliability-based design optimization (RBDO) within engineering challenges has prompted the advancement of saddlepoint approximation methods (SAM) tailored for such problems. This article offers a detailed overview of the general SAM and summarizes the method characteristics first. Subsequently, recent enhancements in the SAM theoretical framework are assessed. Notably, the mean value first-order saddlepoint approximation (MVFOSA) bears resemblance to the conceptual framework of the mean value second-order saddlepoint approximation (MVSOSA); the latter serves as an auxiliary approach to the former. Their distinction is rooted in the varying expansion orders… More >

Fangyi Li^*, Dachang Zhu^*, Huimin Shi

CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.2, pp. 1981-1999, 2024, DOI:10.32604/cmes.2023.031332 - 29 January 2024

Abstract In time-variant reliability problems, there are a lot of uncertain variables from different sources. Therefore, it is important to consider these uncertainties in engineering. In addition, time-variant reliability problems typically involve a complex multilevel nested optimization problem, which can result in an enormous amount of computation. To this end, this paper studies the time-variant reliability evaluation of structures with stochastic and bounded uncertainties using a mixed probability and convex set model. In this method, the stochastic process of a limit-state function with mixed uncertain parameters is first discretized and then converted into a time-independent reliability More >