Zhenke Duan

Zhenke Duan, Xin Li

The explosion of big social data has created a scalability trap for traditional qualitative research, as manual coding remains labor-intensive and conventional topic models often suffer from semantic thinning and a lack of domain awareness. This paper introduces Textual Hybrid Embedding based Topic Analysis (THETA), a novel computational paradigm and open-source tool designed to bridge the gap between massive data scale and rich theoretical depth. THETA moves beyond frequency-based statistics by implementing Domain-Adaptive Fine-tuning (DAFT) via LoRA on foundation embedding models, which effectively optimizes semantic vector structures within specific social contexts to capture latent meanings. To ensure epistemological rigor, we encapsulate this process into an AI Scientist Agent framework, comprising Data Steward, Modeling Analyst, and Domain Expert agents, to simulate the human-in-the-loop expert judgment and constant comparison processes central to grounded theory. Departing from purely computational models, this framework enables agents to iteratively evaluate algorithmic clusters, perform cross-topic semantic alignment, and refine raw outputs into logically consistent theoretical categories. To validate the effectiveness of THETA, we conducted experiments across six domains, including financial regulation and public health. Our results demonstrate that THETA significantly outperforms traditional models, such as LDA, ETM, and CTM, in capturing domain-specific interpretive constructs while maintaining superior coherence. By providing an interactive analysis platform, THETA democratizes advanced natural language processing for social scientists and ensures the trustworthiness and reproducibility of research findings. Code is available at https://github.com/CodeSoul-co/THETA.

Jiqun Pan, Zhenke Duan, Jiani Tu et al.

Industrial question-answering (QA) systems require higher safety and reliability than general-purpose dialogue models, as errors in high-risk scenarios such as equipment fault diagnosis can have severe consequences. Although multi-agent large language models enhance reasoning depth, they suffer from uncontrolled iterations and unverifiable outputs, and conventional distillation methods struggle to transfer collaborative reasoning capabilities to lightweight, deployable student models. To address these challenges, we propose Knowledge Graph-guided Multi-Agent System Distillation (KG-MASD). Our approach formulates distillation as a Markov Decision Process and incorporates a knowledge graph as a verifiable structured prior to enrich state representation and ensure convergence. By integrating collaborative reasoning with knowledge grounding, KG-MASD generates high-confidence instruction-tuning data and jointly distills reasoning depth and verifiability into compact student models suitable for edge deployment. Experiments on an industrial QA dataset show that KG-MASD improves accuracy by 2.4 per cent to 20.1 per cent over baselines and significantly enhances reliability, enabling trustworthy AI deployment in safety-critical industrial scenarios. Code and data are available at https://github.com/erwinmsmith/KG-MAD/.

Zhenke Duan, Jiqun Pan, Jiani Tu et al.

In the era of large-scale artificial intelligence, Large Language Models (LLMs) have made significant strides in natural language processing. However, they often lack transparency and generate unreliable outputs, raising concerns about their interpretability. To address this, the Chain of Thought (CoT) prompting method structures reasoning into step-by-step deductions. Yet, not all reasoning chains are valid, and errors can lead to unreliable conclusions. We propose ECCoT, an End-to-End Cognitive Chain of Thought Validation Framework, to evaluate and refine reasoning chains in LLMs. ECCoT integrates the Markov Random Field-Embedded Topic Model (MRF-ETM) for topic-aware CoT generation and Causal Sentence-BERT (CSBert) for causal reasoning alignment. By filtering ineffective chains using structured ordering statistics, ECCoT improves interpretability, reduces biases, and enhances the trustworthiness of LLM-based decision-making. Key contributions include the introduction of ECCoT, MRF-ETM for topic-driven CoT generation, and CSBert for causal reasoning enhancement. Code is released at: https://github.com/erwinmsmith/ECCoT.git.

Weichao Pan, Bohan Xu, Xu Wang et al.

Fire detection in dynamic environments faces continuous challenges, including the interference of illumination changes, many false detections or missed detections, and it is difficult to achieve both efficiency and accuracy. To address the problem of feature extraction limitation and information loss in the existing YOLO-based models, this study propose You Only Look Once for Fire Detection with Attention-guided Inverted Residual and Dual-pooling Downscale Fusion (YOLO-FireAD) with two core innovations: (1) Attention-guided Inverted Residual Block (AIR) integrates hybrid channel-spatial attention with inverted residuals to adaptively enhance fire features and suppress environmental noise; (2) Dual Pool Downscale Fusion Block (DPDF) preserves multi-scale fire patterns through learnable fusion of max-average pooling outputs, mitigating small-fire detection failures. Extensive evaluation on two public datasets shows the efficient performance of our model. Our proposed model keeps the sum amount of parameters (1.45M, 51.8% lower than YOLOv8n) (4.6G, 43.2% lower than YOLOv8n), and mAP75 is higher than the mainstream real-time object detection models YOLOv8n, YOL-Ov9t, YOLOv10n, YOLO11n, YOLOv12n and other YOLOv8 variants 1.3-5.5%. For more details, please visit our repository: https://github.com/JEFfersusu/YOLO-FireAD

Zhenke Duan, Jiqun Pan, Jiani Tu

Accurate detection of ethylene concentrations in mixed gases is crucial in chemical production for safety and health purposes. Traditional methods are hindered by high cost and complexity, limiting their practical application. This study proposes MENGLAN, a Multiscale Enhanced Nonparametric Gas Analyzer that integrates a dual-stream structure, a Hybrid Multi-Head Attention mechanism, and a Feature Reactivation Module to enable real-time, lightweight, and high-precision ethylene concentration prediction. Results show that MENGLAN achieves superior performance, reduced computational demand, and enhanced deployability compared to existing methods.