Selected work

Representative Papers

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch

Aug 10, 2026

This study addresses the gap in existing large language model (LLM) evaluation frameworks, which often neglect public administration values and Dutch linguistic characteristics. Through expert consultation, user surveys, and civil servant interviews, the authors develop “Grip on LLMs,” a systematic evaluation framework tailored for Dutch government applications. It assesses over thirty general-purpose and Dutch-specific models across six dimensions: factuality, honesty, social bias, energy consumption, cost, and training data transparency. Innovatively integrating public governance principles with local language requirements, the work introduces a multi-dimensional trade-off perspective, revealing that factuality and honesty are governed by distinct mechanisms. A visualization tool is also developed to support non-technical decision-makers in model selection. Findings indicate no single model dominates across all criteria; high performance frequently entails greater environmental and economic costs, and bias shows no significant correlation with model capability. The results are publicly released as an accessible, multi-stakeholder model overview platform.

0 citationsRead paper

A Perturbation and Speciation-Based Algorithm for Dynamic Optimization Uninformed of Change

May 16, 2025

For dynamic optimization problems (DOPs) where environmental changes occur without prior knowledge, this paper proposes PSPSO—a robust evolutionary algorithm that operates without explicit change detection. PSPSO employs a multi-population cyclic evolution framework integrating speciation-based clustering, individual deactivation, and a novel perception-free random perturbation strategy, coupled with periodic resource reallocation for dynamic self-adaptation. In contrast to conventional change-detection-dependent paradigms, PSPSO achieves state-of-the-art performance on the GMPB benchmark, significantly outperforming existing perception-free algorithms—particularly in high-dimensional and high-frequency change scenarios. Ablation studies confirm that the random perturbation component is critical to its performance gain. This work establishes a new paradigm for dynamic optimization and delivers an efficient, practical solver.

0 citationsRead paper

Recent publications

Latest Papers

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch

Aug 10, 2026

This study addresses the gap in existing large language model (LLM) evaluation frameworks, which often neglect public administration values and Dutch linguistic characteristics. Through expert consultation, user surveys, and civil servant interviews, the authors develop “Grip on LLMs,” a systematic evaluation framework tailored for Dutch government applications. It assesses over thirty general-purpose and Dutch-specific models across six dimensions: factuality, honesty, social bias, energy consumption, cost, and training data transparency. Innovatively integrating public governance principles with local language requirements, the work introduces a multi-dimensional trade-off perspective, revealing that factuality and honesty are governed by distinct mechanisms. A visualization tool is also developed to support non-technical decision-makers in model selection. Findings indicate no single model dominates across all criteria; high performance frequently entails greater environmental and economic costs, and bias shows no significant correlation with model capability. The results are publicly released as an accessible, multi-stakeholder model overview platform.

0 citationsRead paper

A Perturbation and Speciation-Based Algorithm for Dynamic Optimization Uninformed of Change

May 16, 2025

For dynamic optimization problems (DOPs) where environmental changes occur without prior knowledge, this paper proposes PSPSO—a robust evolutionary algorithm that operates without explicit change detection. PSPSO employs a multi-population cyclic evolution framework integrating speciation-based clustering, individual deactivation, and a novel perception-free random perturbation strategy, coupled with periodic resource reallocation for dynamic self-adaptation. In contrast to conventional change-detection-dependent paradigms, PSPSO achieves state-of-the-art performance on the GMPB benchmark, significantly outperforming existing perception-free algorithms—particularly in high-dimensional and high-frequency change scenarios. Ablation studies confirm that the random perturbation component is critical to its performance gain. This work establishes a new paradigm for dynamic optimization and delivers an efficient, practical solver.

0 citationsRead paper