Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity or network anomalies, struggle to capture the nuanced relationship between a citation's context and its place in the wider network. While large language models (LLMs) offer powerful capabilities in semantic reasoning for this task, their deployment is hindered by hallucination risks and high computational costs. In this work, we introduce LLM-Augmented Graph Learning-based Miscitation Detector (LAGMiD), a novel framework that leverages LLMs for deep semantic reasoning over citation graphs and distills this knowledge into graph neural networks (GNNs) for efficient and scalable miscitation detection. Specifically, LAGMiD introduces an evidence-chain reasoning mechanism, which uses chain-of-thought prompting, to perform multi-hop citation tracing and assess semantic fidelity. To reduce LLM inference costs, we design a knowledge distillation method aligning GNN embeddings with intermediate LLM reasoning states. A collaborative learning strategy further routes complex cases to the LLM while optimizing the GNN for structure-based generalization. Experiments on three real-world benchmarks show that LAGMiD achieves state-of-the-art miscitation detection with significantly reduced inference cost.

Abstract Scientific text classification is essential for efficiently organizing and assimilating scientific knowledge. However, existing methods struggle to classify ultra‐short scientific texts due to their limited content and complex hierarchical labeling. To overcome these challenges, we introduce the BERT‐HMCN framework, which combines Bidirectional Encoder Representations from Transformers (BERT) with a Hierarchical Multi‐label Classification Network (HMCN). This framework introduces a novel level‐fixed fine‐tuning strategy that strengthens the connection between text semantics and hierarchical labels, enhancing the representation of ultra‐short texts. We evaluated BERT‐HMCN's performance on a dataset of 75,065 program titles from the National Natural Science Foundation of China. Our results show that BERT‐HMCN outperforms existing models in both overall performance and hierarchical accuracy. We also conducted a comparative analysis with autoregressive large language models (LLMs), illustrating the strengths of each in different contexts. Further analysis confirms the effectiveness and robustness of the BERT‐HMCN framework. We discuss its theoretical contributions and practical applications, underscoring the broader implications of these results in scientific text classification and other related fields.

In the current wave of technological innovation, the scientific and technological evaluation system not only plays a crucial role in assessing scientific research achievements but also serves as a driving force for advancing scientific research. To enhance the effectiveness and accuracy of peer review in the scientific and technological evaluation system, an integrating fuzzy C-Means clustering algorithm and similarity analysis method is proposed. In this methodology, the fuzzy C-Means clustering algorithm is first applied to conduct cluster analysis on expert feature attribute. Second, the recursive feature elimination feature selection is used to select the important features for enhancing the model generalization capability. The Gower distance of key features between experts is calculated to determine the similarity between experts, and the association features among experts are mined. Finally, an expert credibility prediction model is constructed based on a feedforward neural network. A real-world expert credibility dataset was used to validate the effectiveness and feasibility of the proposed method. The experimental results indicated that integrating the fuzzy C-Means clustering algorithm and similarity association is an effective way to improve the model prediction performance. This can be considered a promising solution for the scientific and technological evaluation.

Graph Neural Networks (GNNs) have gained attention for their ability in capturing node interactions to generate node representations. However, their performances are frequently restricted in real-world directed networks with natural hierarchical structures. Most current GNNs incorporate information from immediate neighbors or within predefined receptive fields, potentially overlooking long-range dependencies inherent in hierarchical structures. They also tend to neglect node adaptability, which varies based on their positions. To address these limitations, we propose a new model called Hierarchy-Aware Adaptive Graph Neural Network (HAGNN) to adaptively capture hierarchical long-range dependencies. Technically, HAGNN creates a hierarchical structure based on directional pair-wise node interactions, revealing underlying hierarchical relationships among nodes. The inferred hierarchy helps to identify certain key nodes, named Source Hubs in our research, which serve as hierarchical contexts for individual nodes. Shortcuts adaptively connect these Source Hubs with distant nodes, enabling efficient message passing for informative long-range interactions. Through comprehensive experiments across multiple datasets, our proposed model outperforms several baseline methods, thus establishing a new state-of-the-art in performance. Further analysis demonstrates the effectiveness of our approach in capturing relevant adaptive hierarchical contexts, leading to improved and explainable node representation.

Risk measures play significant roles in determining the magnitude of risks. The traditional risk measures consider only the consequence (C) and the probability (P) and ignore the support of the knowledge behind to estimate C and P. Several researchers have suggested adding knowledge as a third dimension in the risk measures. However, the issues of how to embed the dimension of knowledge in the risk measures to output an explicit expression of the risk measure and how to measure the strength of knowledge remain unresolved. This paper proposes a new risk measure incorporating the dimension of knowledge, apart from C and P. It is shown that the proposed risk measure has the form of traditional risk measures when the risk assessor has full knowledge. In addition, a fuzzy multicriteria decision-making (MCDM) method is employed to assess the strength of knowledge. In the fuzzy MCDM method, an entropy optimization problem is solved to obtain fuzzy measures, which are critical for determining the score of the strength of knowledge. Finally, the proposed method is applied to a project risk assessment, showing the feasibility of the method.