Weishen Chu

Dr. Weishen Chu


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2025 in AI
Verified
Journal Article
Open access
PDF file
XLXiaoming Liu
Xiaoming Liu
DHDanni Huang
Danni Huang
JYJingyu Yao
Jingyu Yao
JDJing Dong
Jing Dong
LSLitong Song
Litong Song
WCWeishen Chu
Weishen Chu
Explainable Artificial Intelligence (XAI) has become essential as machine learning systems are deployed in high-stakes domains such as security, finance, and healthcare. Traditional models often act as “black boxes”, limiting trust and accountability. Traditional models often act as “black boxes”, limiting trust and accountability. However, most existing reviews treat explainability either as a technical problem or a philosophical issue, without connecting interpretability techniques to their real-world implications for security, privacy, and governance. This review fills that gap by integrating theoretical foundations with practical applications and societal perspectives. define transparency and interpretability as core concepts and introduce new economics-inspired notions of marginal transparency and marginal interpretability to highlight diminishing returns in disclosure and explanation. Methodologically, we examine model-agnostic approaches such as LIME and SHAP, alongside model-specific methods including decision trees and interpretable neural networks. We also address ante-hoc vs. post hoc strategies, local vs. global explanations, and emerging privacy-preserving techniques. To contextualize XAI’s growth, we integrate capital investment and publication trends, showing that research momentum has remained resilient despite market fluctuations. Finally, we propose a roadmap for 2025–2030, emphasizing evaluation standards, adaptive explanations, integration with Zero Trust architectures, and the development of self-explaining agents supported by global standards. By combining technical insights with societal implications, this article provides both a scholarly contribution and a practical reference for advancing trustworthy AI.

8 December 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
QLQiuyue Liao
Qiuyue Liao
YCYue Chen
Yue Chen
SHShuangjiang He
Shuangjiang He
RWRuiqi Wang
Ruiqi Wang
WXWei Xu
Wei Xu
WCWeishen Chu
Weishen Chu
Explainable artificial intelligence (XAI) plays a central role in strengthening security, privacy, and trust in AI-driven 5G and future 6G networks. In this review, we first re-fine the concepts of transparency and interpretability, and introduce the notions of marginal transparency and marginal interpretability to describe the diminishing re-turns that arise from progressively deeper disclosure of model internals. We then survey key XAI methods, including LIME, SHAP, interpretable neural networks, and federated, privacy-preserving techniques, and assess their suitability for wireless re-source management, intrusion detection, and regulatory auditing in next-generation networks. Building on these foundations, we outline a 2025–2030 research roadmap that integrates XAI into Zero Trust architectures, edge intelligence, and self-explaining 6G systems. Across these layers, we argue that explainability should be built in as a design-time requirement, enabling wireless infrastructures that are not only high performance but also auditable, accountable, and resilient.

8 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
JYJingyu Yao
Jingyu Yao
YZYao Zhou
Yao Zhou
YZYuncong Zuo
Yuncong Zuo
CYChenchen Yu
Chenchen Yu
WCWeishen Chu
Weishen Chu
Autonomous vehicles (AVs) must recognize weather and lighting conditions that affect perception and driving decisions. Classification accuracy alone, however, does not reveal which visual evidence a model uses. We apply explainable artificial intelligence (XAI) to condition recognition on 31,420 CARLA images spanning 21 weather–time classes. ResNet18 and ResNet50 are compared with global color baselines, and Grad-CAM and Integrated Gradients (IG) explain predictions from a designated ResNet18 model. Across three training seeds, the neural models achieve internal joint accuracies of 99.547 ± 0.123% and 99.710 ± 0.117%, respectively (mean ± sample standard deviation), with detected structural-similarity groups kept within partitions. Analysis of 210 correct and all 18 incorrect predictions reveals masking sensitivity to replacement choices and prediction correctness. After full parameter randomization, signed IG correlations approach zero while positive-grid correlations remain around 0.4, showing that different attribution representations can yield different assessments. These findings demonstrate how explanatory analysis complements accuracy in evaluating AV perception models, while independent-route generalization remains unverified. Future work will extend the analysis from simulation to real driving images using the Adverse Conditions Dataset with Correspondences (ACDC), with compatible tasks for comparing explanations across domains. This simulation-to-real extension aims to inform the development of explanation-aware AV benchmarks that evaluate predictive performance alongside explanation robustness.

17 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
DHDanni Huang
Danni Huang
LSLitong Song
Litong Song
YCYue Chen
Yue Chen
SHShuangjiang He
Shuangjiang He
RWRuiqi Wang
Ruiqi Wang
WCWeishen Chu
Weishen Chu
This study proposes an explainable artificial intelligence (XAI) engineering workflow for provider-level healthcare claim audit prioritization using SHAP-guided hybrid retrieval-augmented generation (RAG). The framework integrates provider-level claim aggregation, tree-based risk screening, SHAP explanation, exploratory group-level SHAP clustering, policy concept retrieval, and constrained large language model audit narrative generation. Experiments on a public Medicare provider fraud dataset use the dataset-provided PotentialFraud label as a weak audit prioritization label rather than a legal determination of fraud. The results show that reimbursement exposure, utilization duration, claim repetition, deductible patterns, and beneficiary case mix contribute to provider-level risk scores. Additional cross-validation, calibration, threshold, and scale-confounding analyses indicate that provider size and financial exposure are important confounders, while non-scale and contextual features also retain predictive information. Beyond prediction, the framework organizes local SHAP drivers into exploratory provider archetypes and maps explanation patterns to audit-relevant policy concepts. Compared with pure embedding retrieval, the SHAP-guided hybrid retriever increases policy concept diversity and explanation alignment, although these retrieval metrics do not replace independent expert audit validation. Because the public dataset does not include referral pathways, inter-facility transfers, provider-network relationships, or care-coordination records, the framework cannot determine whether utilization patterns are explained by clinically appropriate referrals, regional access constraints, or multi-level care pathways. Its current applicability is therefore limited to provider-level audit prioritization using the available claims and beneficiary variables. The proposed system is positioned as a reproducible engineering prototype for cautious, human-reviewed audit support rather than a comprehensive or automated fraud determination system.

29 December 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
WCWeishen Chu
Weishen Chu
Risk factor disclosures in corporate filings are widely analyzed for their informational content, yet their usefulness for operational governance remains underexplored. This paper introduces risk actionability as a distinct concept from risk presence and proposes an interpretable, agent-based pipeline for assessing whether disclosed risks support intervention-oriented decisions. Operating at the paragraph level on SEC Form 10-K and 10-Q risk factors, the agent assigns risk attributes and maps disclosures to pass, review, or escalate states. We introduce the Intervention Load Index and Actionability Gap to quantify human oversight demand implied by disclosures. Empirical results show that disclosure severity does not reliably predict intervention needs, and that conservative disclosure styles can suppress actionable signals. A failure case highlights limitations arising from disclosure sparsity.

Verified
Journal Article
Open access
PDF file
DHDanni Huang
Danni Huang
LSLitong Song
Litong Song
YCYue Chen
Yue Chen
SHShuangjiang He
Shuangjiang He
RWRuiqi Wang
Ruiqi Wang
WCWeishen Chu
Weishen Chu
This study proposes an explainable artificial intelligence (XAI) engineering workflow for provider-level healthcare claim audit prioritization using SHAP-guided hybrid retrieval-augmented generation (RAG). The framework integrates provider-level claim aggregation, tree-based risk screening, SHAP explanation, exploratory group-level SHAP clustering, policy concept retrieval, and constrained large language model audit narrative generation. Experiments on a public Medicare provider fraud dataset use the dataset-provided PotentialFraud label as a weak audit prioritization label rather than a legal determination of fraud. The results show that reimbursement exposure, utilization duration, claim repetition, deductible patterns, and beneficiary case mix contribute to provider-level risk scores. Additional cross-validation, calibration, threshold, and scale-confounding analyses indicate that provider size and financial exposure are important confounders, while non-scale and contextual features also retain predictive information. Beyond prediction, the framework organizes local SHAP drivers into exploratory provider archetypes and maps explanation patterns to audit-relevant policy concepts. Compared with pure embedding retrieval, the SHAP-guided hybrid retriever increases policy concept diversity and explanation alignment, although these retrieval metrics do not replace independent expert audit validation. Because the public dataset does not include referral pathways, inter-facility transfers, provider–network relationships, or care-coordination records, the framework cannot determine whether utilization patterns are explained by clinically appropriate referrals, regional access constraints, or multi-level care pathways. Its current applicability is therefore limited to provider-level audit prioritization using the available claims and beneficiary variables. The proposed system is positioned as a reproducible engineering prototype for cautious, human-reviewed audit support rather than a comprehensive or automated fraud determination system.