Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness in domain-specific applications that require specialized knowledge, such as healthcare, chemistry, or legal analysis. To address this, researchers have explored diverse methods to enhance LLMs by integrating domain-specific knowledge. In this survey, we provide a comprehensive overview of these methods, which we categorize into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization. Each approach offers unique mechanisms to equip LLMs with domain expertise, balancing trade-offs between flexibility, scalability, and efficiency. We discuss how these methods enable LLMs to tackle specialized tasks, compare their advantages and disadvantages, evaluate domain-specific LLMs against general LLMs, and highlight the challenges and opportunities in this emerging field. For those interested in delving deeper into this area, we also summarize the commonly used datasets and benchmarks. To keep researchers updated on the latest studies, we maintain an open-source at: https://github.com/abilliyb/Knowledge_Injection_Survey_Papers, dedicated to documenting research in the field of specialized LLM.

The deep neural network has attained significant efficiency in image recognition. However, it has vulnerable recognition robustness under extensive data uncertainty in practical applications. The uncertainty is attributed to the inevitable ambient noise and, more importantly, the possible adversarial attack. Dynamic methods can effectively improve the defense initiative in the arms race of attack and defense of adversarial examples. Different from the previous dynamic method depend on input or decision, this work explore the dynamic attributes in model level through dynamic ensemble selection technology to further protect the model from white-box attacks and improve the robustness. Specifically, in training phase the Dirichlet distribution is apply as prior of sub-models' predictive distribution, and the diversity constraint in parameter space is introduced under the lightweight sub-models to construct alternative ensembel model spaces. In test phase, the certain sub-models are dynamically selected based on their rank of uncertainty value for the final prediction to ensure the majority accurate principle in ensemble robustness and accuracy. Compared with the previous dynamic method and staic adversarial traning model, the presented approach can achieve significant robustness results without damaging accuracy by combining dynamics and diversity property.

However, the existence of automated accounts, also known as social bots, has brought many problems to social media. These bots have been employed to disseminate false information, manipulate elections, and deceive users, resulting in negative societal consequences [1; 2; 3]. Effectively detecting bots on social media plays an important role in protecting user interests and ensuring stable platform operation. Therefore, the accurate detection of bots on social media platforms is becoming increasingly crucial. Random Forest (RF) [4] is a classical algorithm of ensemble learning that can significantly improve the performance of the base classifier, Decision Tree (DT) [5]. Specifically, S sub-training sets are generated by randomly selecting n samples with replacement from the original training set of N samples S times. Then, m features are selected from the M-dimensional features of each sub-training set, and S base classifiers are trained using different sub-training sets. The final classification result is determined by the voting of the base classifiers. Due to its excellent performance, RF has been widely applied in various competitions, such as data mining and financial risk detection, and is also frequently used in social bot detection.

The Graph Convolutional Networks (GCNs) have achieved excellent results in node classification tasks, but the model's performance at low label rates is still unsatisfactory. Previous studies in Semi-Supervised Learning (SSL) for graph have focused on using network predictions to generate soft pseudo-labels or instructing message propagation, which inevitably contains the incorrect prediction due to the over-confident in the predictions. Our proposed Dual-Channel Consistency based Graph Convolutional Networks (DCC-GCN) uses dual-channel to extract embeddings from node features and topological structures, and then achieves reliable low-confidence and high-confidence samples selection based on dual-channel consistency. We further confirmed that the low-confidence samples obtained based on dual-channel consistency were low in accuracy, constraining the model's performance. Unlike previous studies ignoring low-confidence samples, we calibrate the feature embeddings of the low-confidence samples by using the neighborhood's high-confidence samples. Our experiments have shown that the DCC-GCN can more accurately distinguish between low-confidence and high-confidence samples, and can also significantly improve the accuracy of low-confidence samples. We conducted extensive experiments on the benchmark datasets and demonstrated that DCC-GCN is significantly better than state-of-the-art baselines at different label rates.

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-GNN), a self-supervised learning framework for Graph Neural Network, which learns feature representations of sample data without data labels. AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks. AMC-GNN could learn the importance weights of embeddings in different layers adaptively through the attention mechanism, and an auxiliary encoder is introduced to train graph contrastive encoders better. The accuracy is improved by maximizing the representation's consistency of positive pairs in the early layers and the final embedding space. Our experiments show that the results can be consistently improved by using the AMC-GNN framework, across four established graph benchmarks: Cora, Citeseer, Pubmed, DBLP citation network datasets, as well as four newly proposed datasets: Co-author-CS, Co-author-Physics, Amazon-Computers, Amazon-Photo.