Recently, prompt-based learning has shown impressive performance on various natural language processing tasks in few-shot scenarios. The previous study of knowledge probing showed that the success of prompt learning contributes to the implicit knowledge stored in pre-trained language models. However, how this implicit knowledge helps solve downstream tasks remains unclear. In this work, we propose a knowledge-guided prompt learning method that can reveal relevant knowledge for text classification. Specifically, a knowledge prompting template and two multi-task frameworks were designed, respectively. The experiments demonstrated the superiority of combining knowledge and prompt learning in few-shot text classification.

Knowledge base question answering (KBQA) aims to provide answers to natural language questions from information in the knowledge base. Although many methods perform well when dealing with simple questions, there are still two challenges for complex questions: huge search space and information missing from the query graphs’ structure. To solve these problems, we propose a novel KBQA method based on a graph convolutional network and optimized search space. When generating the query graph, we rank the query graphs by both their semantic and structural similarities with the question. Then, we just use the top k for the next step. In this process, we specifically extract the structure information of the query graphs by a graph convolutional network while extracting semantic information by a pre-trained model. Thus, we can enhance the method’s ability to understand complex questions. We also introduce a constraint function to optimize the search space. Furthermore, we use the beam search algorithm to reduce the search space further. Experiments on the WebQuestionsSP dataset demonstrate that our method outperforms some baseline methods, showing that the structural information of the query graph has a significant impact on the KBQA task.

Depression affects approximately 280 million people worldwide, yet remains substantially underdiagnosed due to the limitations of clinical assessment tools. This systematic review synthesizes 38 studies (2013--2025) on AI-based depression detection across voice, facial expression, physiological signals, and social media modalities, following PRISMA 2020 guidelines. Multimodal fusion consistently outperforms unimodal approaches, with reported F1 gains of 5-15% on benchmark datasets; however, no reviewed system has undergone prospective clinical validation, and reported accuracy figures should be interpreted as upper bounds on clinical utility. Critical open challenges include cross-cultural generalizability, longitudinal monitoring, interpretability, and ethical governance. This review reframes the field's central question from can AI detect depression? to under what conditions and with what governance can it be safely deployed?