arXiv subjects

Mingzi Zhang

Publications and source records attributed to Mingzi Zhang.

13 recordsLinked to original sources

arXiv2026

Measuring the Professional Educational Competence of Foundation Models

Foundation models tutor, assess, and instruct at population scale, requiring externally defined measures of educational competence. Existing benchmarks emphasize difficult academic problems or isolated synthetic educational tasks rather than authentic teacher-entry standards. We introduce EDU 1.0 (Educational Due Diligence for Foundation Models), which uses teacher-entry assessments as proxies for educational competence rather than substitutes for human qualification. EDU 1.0 comprises 10,012 questions from teacher certification and recruitment examinations in the United States, China, and India, including the U.S. Praxis series, China's National Teacher Qualification Examination, and India's Kendriya Vidyalaya Sangathan examinations. It covers foundational literacy and knowledge, pedagogical principles, and subject-specific pedagogical expertise across language arts, mathematics, science, social science, and education practice. Across 36 foundation-model variants, the strongest proprietary model reaches a response-balanced score of 96.5%; the leading open-weight model trails by 2.1 percentage points, while the leading system deployable on a single accelerator reaches 92.2%. These aggregates conceal a shared limitation: all three systems score higher on general pedagogical principles than on assessments requiring pedagogy to be applied within a discipline. Their subject-assessment scores span 4.1-8.8 points, and their shortfall relative to general pedagogy widens from 2.6 to 4.1 points as capability declines. The outstanding requirement is therefore pedagogical content knowledge, the capacity to make particular subject matter teachable to particular learners, rather than general pedagogy or model scale.

cs.CY↗

arXiv2026

Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts

As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric evaluations neglect the visual modality, leaving an unregulated channel for latent social biases. To bridge this gap, we present Edu-MMBias, a systematic auditing framework grounded in the tri-component model of attitudes from social psychology. This framework diagnoses bias across three hierarchical dimensions: cognitive, affective, and behavioral. Utilizing a specialized generative pipeline that incorporates a self-correct mechanism and human-in-the-loop verification, we synthesize contamination-resistant student profiles to conduct a holistic stress test on state-of-the-art VLMs. Our extensive audit reveals critical, counter-intuitive patterns: models exhibit a compensatory class bias favoring lower-status narratives while simultaneously harboring deep-seated health and racial stereotypes. Crucially, we find that visual inputs act as a safety backdoor, triggering a resurgence of biases that bypass text-based alignment safeguards and revealing a systematic misalignment between latent cognition and final decision-making. The contributions of this paper are available at: https://anonymous.4open.science/r/EduMMBias-63B2.

cs.AI↗

arXiv2026

EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content

Large language models are increasingly used as educational assistants, yet evaluation of their educational capabilities remains concentrated on question-answering and tutoring tasks. A critical gap exists for multimedia instructional content generation -- the ability to produce coherent, diagram-rich explanations that combine geometrically accurate visuals with step-by-step reasoning. We present EduIllustrate, a benchmark for evaluating LLMs on interleaved text-diagram explanation generation for K-12 STEM problems. The benchmark comprises 230 problems spanning five subjects and three grade levels, a standardized generation protocol with sequential anchoring to enforce cross-diagram visual consistency, and an 8-dimension evaluation rubric grounded in multimedia learning theory covering both text and visual quality. Evaluation of ten LLMs reveals a wide performance spread: Gemini 3.0 Pro Preview leads at 87.8\%, while Kimi-K2.5 achieves the best cost-efficiency (80.8\% at \\$0.12/problem). Workflow ablation confirms sequential anchoring improves Visual Consistency by 13\% at 94\% lower cost. Human evaluation with 20 expert raters validates LLM-as-judge reliability for objective dimensions ($ρ\geq 0.83$) while revealing limitations on subjective visual assessment.

cs.CY↗

arXiv2026

Influence of Plaque Characteristics on Stent Biomechanical Outcomes - A Case Study on Double Kissing Crush Coronary Stenting

Background Double Kissing (DK) Crush is a two-stent technique for complex coronary bifurcation lesions, yet the biomechanical influence of plaque on its performance remains poorly understood. This study developed a computational biomechanical model of the DK-Crush procedure to quantify how plaque presence and composition affect procedural outcomes and the performance of Xience Sierra and Orsiro stents. Methods A population-representative coronary bifurcation was modelled with no plaque, lipid plaque, and fibrous plaque. The complete DK-Crush sequence was simulated using finite element analysis for both stent platforms. Mechanical outcomes included arterial wall stress, malapposition, side branch ostium clearance, and residual stenosis. Post-deployment hemodynamics was assessed using pulsatile computational fluid dynamics, quantifying high shear rate volume and lumen area exposed to low time-averaged endothelial shear stress (TAESS). Results Plaque presence and stiffness reduced lumen restoration, increased arterial wall stress, led to larger high shear rate regions and, for fibrous plaque, increased exposure to low TAESS. Malapposition and ostial clearance depended mainly on stent design. Plaque also altered the relative performance of the two platforms, revealing differences not observed in plaque-free models. Conclusions Plaque characteristics substantially affect DK-Crush biomechanics and modify stent behaviour. Incorporating plaque is therefore essential for realistic computational evaluation of bifurcation stenting.

physics.bio-ph↗

arXiv2025

Are Ultrathin Stents Optimal for Bifurcation Lesions? Insights from Computational Modelling of Provisional and DK-Crush Techniques

Complex coronary bifurcation lesions remain challenging in percutaneous coronary intervention, with stent design and deployment strategy influencing clinical outcomes. This study compares the mechanical and hemodynamic performance of the ultrathin-strut Orsiro and thin-strut Xience Sierra stent in Provisional Side Branch (PSB) and Double Kissing Crush (DKC) techniques. We used finite element analyses of bifurcation stent deployment to assess malapposition, ostium clearance, and arterial wall stress for both techniques. Computational fluid dynamics simulations quantified the luminal exposure to low Time-Averaged Endothelial Shear Stress (TAESS below 0.4 Pa) and high shear rates (above 1000 1/s). In PSB, Orsiro showed higher malapposition (13.0% vs 9.6%) but improved SB ostium clearance (77% vs 64%) and lower low-TAESS exposure (30.3% vs 33.6%) compared to Xience. Orsiro also produced higher arterial wall stresses, particularly during kissing balloon inflation. In DKC, differences in malapposition and ostium clearance diminished between stents, though Orsiro retained a hemodynamic advantage with lower low-TAESS (28.2% vs 36.3%).Stent design influenced outcomes more strongly in PSB, where anatomical interaction and platform-specific behavior impacted both structural and hemodynamic results. In DKC, procedural complexity minimized those differences, making the stenting technique the primary performance driver. Nonetheless, Orsiro consistently preserved more favorable flow conditions. These findings highlight the need to match device selection with lesion characteristics in PSB, while in DKC, optimizing procedural steps may have a greater impact than the choice of stent platform.

physics.med-ph↗

arXiv2025

EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers

Large Language Models for Simulating Professions (SP-LLMs), particularly as teachers, are pivotal for personalized education. However, ensuring their professional competence and ethical safety is a critical challenge, as existing benchmarks fail to measure role-playing fidelity or address the unique teaching harms inherent in educational scenarios. To address this, we propose EduGuardBench, a dual-component benchmark. It assesses professional fidelity using a Role-playing Fidelity Score (RFS) while diagnosing harms specific to the teaching profession. It also probes safety vulnerabilities using persona-based adversarial prompts targeting both general harms and, particularly, academic misconduct, evaluated with metrics including Attack Success Rate (ASR) and a three-tier Refusal Quality assessment. Our extensive experiments on 14 leading models reveal a stark polarization in performance. While reasoning-oriented models generally show superior fidelity, incompetence remains the dominant failure mode across most models. The adversarial tests uncovered a counterintuitive scaling paradox, where mid-sized models can be the most vulnerable, challenging monotonic safety assumptions. Critically, we identified a powerful Educational Transformation Effect: the safest models excel at converting harmful requests into teachable moments by providing ideal Educational Refusals. This capacity is strongly negatively correlated with ASR, revealing a new dimension of advanced AI safety. EduGuardBench thus provides a reproducible framework that moves beyond siloed knowledge tests toward a holistic assessment of professional, ethical, and pedagogical alignment, uncovering complex dynamics essential for deploying trustworthy AI in education. See https://github.com/YL1N/EduGuardBench for Materials.

cs.CL↗

arXiv2025

EMNLP: Educator-role Moral and Normative Large Language Models Profiling

Simulating Professions (SP) enables Large Language Models (LLMs) to emulate professional roles. However, comprehensive psychological and ethical evaluation in these contexts remains lacking. This paper introduces EMNLP, an Educator-role Moral and Normative LLMs Profiling framework for personality profiling, moral development stage measurement, and ethical risk under soft prompt injection. EMNLP extends existing scales and constructs 88 teacher-specific moral dilemmas, enabling profession-oriented comparison with human teachers. A targeted soft prompt injection set evaluates compliance and vulnerability in teacher SP. Experiments on 14 LLMs show teacher-role LLMs exhibit more idealized and polarized personalities than human teachers, excel in abstract moral reasoning, but struggle with emotionally complex situations. Models with stronger reasoning are more vulnerable to harmful prompt injection, revealing a paradox between capability and safety. The model temperature and other hyperparameters have limited influence except in some risk behaviors. This paper presents the first benchmark to assess ethical and psychological alignment of teacher-role LLMs for educational AI. Resources are available at https://e-m-n-l-p.github.io/.

cs.CL↗

arXiv2025

Mechanistic Insights Into How Rewiring and Bifurcation Angle Affect DK-Crush Stent Deployment

Background Double Kissing Crush (DKC) is a preferred two-stent technique for complex coronary bifurcation lesions. Proximal cell rewiring is routinely recommended to reduce technical failure, and DKC is considered effective across various bifurcation angles. However, it remains unclear whether this standard approach is optimal for all patients. This study investigates the interaction between bifurcation angle and rewiring configuration to identify anatomy-specific strategies. Methods Computational modeling of the DKC procedure was used to simulate 12 DKC procedures across three left main bifurcation angles (45°, 70°, and 100°) and four rewiring configurations: proximal-proximal (P-P), proximal-distal (P-D), distal-proximal (D-P), and distal-distal (D-D). Evaluation metrics included stent malapposition, side branch ostium clearance, arterial wall stress, low time-averaged endothelial shear stress, and high shear rates. Results DKC performed in wide bifurcations (100°) resulted in worse outcomes, with malapposition reaching 18%, side branch clearance down to 23%, and up to twice the exposure to adverse high shear rates compared to narrower angles. In contrast, intermediate (70°) and narrow (45°) angles generally resulted in more favorable outcomes, though optimal rewiring varied by angle. Proximal strategies, i.e. P-P and P-D, were most effective at 70°, while D-D performed best at 45°. No single strategy was consistently superior across all bifurcation angles. Conclusions DKC outcomes depend on bifurcation angle and can be optimized by tailoring rewiring strategies, challenging the current clinical understanding. These findings support anatomy-specific procedural planning and intravascular imaging to guide rewiring. This study provides a mechanistic rationale to improve clinical decision-making and tailor bifurcation interventions.

physics.med-ph↗

arXiv2025

ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities

Can Multimodal Large Language Models (MLLMs), with capabilities in perception, recognition, understanding, and reasoning, function as independent assistants in art evaluation dialogues? Current MLLM evaluation methods, which rely on subjective human scoring or costly interviews, lack comprehensive coverage of various scenarios. This paper proposes a process-oriented Human-Computer Interaction (HCI) space design to facilitate more accurate MLLM assessment and development. This approach aids teachers in efficient art evaluation while also recording interactions for MLLM capability assessment. We introduce ArtMentor, a comprehensive space that integrates a dataset and three systems to optimize MLLM evaluation. The dataset consists of 380 sessions conducted by five art teachers across nine critical dimensions. The modular system includes agents for entity recognition, review generation, and suggestion generation, enabling iterative upgrades. Machine learning and natural language processing techniques ensure the reliability of evaluations. The results confirm GPT-4o's effectiveness in assisting teachers in art evaluation dialogues. Our contributions are available at https://artmentor.github.io/.

cs.HC↗

arXiv2025

Reliability of characterising coronary artery flow with the flow-split outflow strategy: comparison against the multiscale approach

In computational modelling of coronary haemodynamics, imposing patient-specific flow conditions is paramount, yet often impractical due to resource and time constraints, limiting the ability to perform a large number of simulations particularly for diseased cases. We aimed to compare coronary haemodynamics quantified using a simplified flow-split strategy with varying exponents against the clinically verified but computationally intensive multiscale simulations under both resting and hyperaemic conditions in arteries with varying degrees of stenosis. Six patient-specific left coronary artery trees were segmented and reconstructed, including three with severe (>70%) and three with mild (<50%) focal stenoses. Simulations were performed for the entire coronary tree to account for the flow-limiting effects from epicardial artery stenoses. Both a 0D-3D coupled multiscale model and a flow-split approach with four different exponents (2.0, 2.27, 2.33, and 3.0) were used. The resulting prominent haemodynamic metrics were statistically compared between the two methods. Flow-split and multiscale simulations did not significantly differ under resting conditions regardless of the stenosis severity. However, under hyperaemic conditions, the flow-split method significantly overestimated the time-averaged wall shear stress by up to 16.8 Pa (p=0.031) and underestimate the fractional flow reserve by 0.327 (p=0.043), with larger discrepancies observed in severe stenoses than in mild ones. Varying the exponent from 2.0 to 3.0 within the flow-split methods did not significantly affect the haemodynamic results (p>0.141). Flow-split strategies with exponents between 2.0 and 3.0 are appropriate for modelling stenosed coronaries under resting conditions. Multiscale simulations are recommended for accurate modelling of hyperaemic conditions, especially in severely stenosed arteries.

physics.med-ph↗

arXiv2025

High-Intensity Helical Flow: A Double-Edged Sword in Coronary Artery Haemodynamics

The role of Helical Flow (HF) in human coronary arteries remains uncertain, yet its understanding promises unprecedented insights into atherosclerotic processes. In this study, we investigated the effects of HF and key haemodynamic descriptors in 39 patient-specific left coronary artery trees from the ASOCA dataset, including 20 non-stenosed and 19 stenosed cases. Absolute HF intensity $h_2$ correlated with higher Time-Averaged Endothelial Shear Stress (TAESS) in all vessel segments regardless of stenosis (p < 0.05). In stenosed cases, this correlation was so prominent that the vessel area exposed to adversely low TAESS was reduced (< 0.5 Pa, p = 0.0001), while areas of adversely high TAESS increased (> 4.71 Pa, p < 0.05), coinciding with high $h_2$ regions. This suggests that HF in coronary arteries is not always protective as previously thought. It not only mitigates low TAESS, which is associated with long-term plaque development and restenosis, but also exacerbates adversely high TAESS, which is linked to increased plaque vulnerability and acute events. Our findings redefine the current understanding of helical blood flow's role in cardiovascular atherosclerotic disease processes.

physics.med-ph↗

arXiv2023

Exploring the Interplay of Left Coronary Tree Anatomy and Haemodynamics: Implications for Plaque Formation

The link between atherosclerosis and blood flow-induced haemodynamic luminal shear stresses is well established. However, this understanding has not been translated into clinical practice because of the interdependent effects of the complex coronary anatomy and a multitude of potential haemodynamic metrics, which have been challenging to delineate. Thus, this study aims to identify anatomical and haemodynamic differences in coronary trees at different stages of stenoses. A total of 39 left coronary trees were considered, which are publicly available. Each coronary tree was dissected into bifurcations and non-bifurcating segments for comparisons. We calculated a full set of anatomical metrics and performed transient flow simulations to solve the normalised luminal area exposed to Low Time-Average Endothelial Shear Stress (%LowTAESS), High Oscillatory Shear Index (%HighOSI), and High Relative Residence Time (%HighRRT). We statistically investigated the differences between non-stenosed (n=20, Diameter Stenosis DS=0%), moderately (n=12, 0% =70%) stenosed cases, whereby p<0.05* is considered significant. Only the average curvature and %HighOSI differed between the non-stenosed, and moderately or severely stenosed for the coronary trees (p=0.024* and p<0.001*), and non-bifurcating segments (p=0.027* and p<0.001*). %LowTAESS@0.5Pa and %HighRRT@2.5Pa-1 significantly differed between moderately (0% =70\%) stenosed trees (p=0.009* and p=0.012*). Our findings suggest curvature and potentially %HighOSI being critical factors in coronary plaque onset in non-bifurcating segments, whereas %LowTAESS and %HighRRT affect plaque progression after onset.

physics.med-ph↗

arXiv2023

Sex-Specific Variances in Anatomy and Blood Flow of the Left Main Coronary Bifurcation: Implications for Coronary Artery Disease Risk

Studies have shown marked sex disparities in Coronary Artery Diseases (CAD) epidemiology, yet the underlying mechanisms remain unclear. We explored sex disparities in the coronary anatomy and the resulting haemodynamics in patients with suspected, but no significant CAD. Left Main (LM) bifurcations were reconstructed from CTCA images of 127 cases (42 males and 85 females, aged 38 to 81). Detailed shape parameters were measured for comparison, including bifurcation angles, curvature, and diameters, before solving the haemodynamic metrics using CFD. The severity and location of the normalised vascular area exposed to physiologically adverse haemodynamics were statistically compared between sexes for all branches. We found significant differences between sexes in potentially adverse haemodynamics. Females were more likely than males to exhibit adversely low Time Averaged Endothelial Shear Stress along the inner wall of a bifurcation (16.8% vs. 10.7%). Males had a higher percentage of areas exposed to both adversely high Relative Residence Time (6.1% vs 4.2%, p=0.001) and high Oscillatory Shear Index (4.6% vs 2.3%, p<0.001). However, the OSI values were generally small and should be interpreted cautiously. Males had larger arteries (M vs F, LM: 4.0mm vs 3.3mm, LAD: 3.6mm 3.0mm, LCX:3.5mm vs 2.9mm), and females exhibited higher curvatures in all three branches (M vs F, LM: 0.40 vs 0.46, LAD: 0.45 vs 0.51, LCx: 0.47 vs 0.55, p<0.001) and larger inflow angle of the LM trunk (M: 12.9° vs F: 18.5°, p=0.025). Haemodynamic differences were found between male and female patients, which may contribute, at least in part, to differences in CAD risk. This work may facilitate a better understanding of sex differences in the clinical presentation of CAD, contributing to improved sex-specific screening, especially relevant for women with CAD who currently have worse predictive outcomes.

physics.med-ph↗