Mingxiu Sui

Faced with the challenges of accelerating growth in unstructured text data and increasing risk concealment in the financial market, this study constructs a financial risk assessment system that combines text mining with large language models (LLMs). This system forms an end-to-end architecture encompassing data, knowledge, models, services, and governance. The system collects multi source text, constructs a risk knowledge graph, and extracts key events and sentiment signals. These are then integrated into the LLM framework of retrieval augmented generation (RAG) and multi feature fusion to achieve credit risk prediction and default probability estimation. This experiment relies on the FinBen Lending Club dataset (2024) and conducts comparative experiments, ablation studies, error analysis, and stability tests. The model outperforms traditional structured models and plain text models in key evaluation indicators such as F1, MCC, and PR AUC. In scenarios of market environment changes, cross industry migration, and anti-interference, the model’s stability and compliance performance are outstanding. This study designs an intelligent risk identification solution for financial institutions, which makes the identification process explainable, traceable, and auditable. This study has significant theoretical and practical impact on risk governance and decision support for banks, securities, insurance, and regulatory authorities.

Effective communication in automated chat systems hinges on the ability to understand and respond to context. Traditional models often struggle with determining when additional context is necessary for generating appropriate responses. This paper introduces Context-Aware BERT (CA-BERT), a transformer-based model specifically fine-tuned to address this challenge. CA-BERT innovatively applies deep learning techniques to discern context necessity in multi-turn chat interactions, enhancing both the relevance and accuracy of responses. We describe the development of CA-BERT, which adapts the robust architecture of BERT with a novel training regimen focused on a specialized dataset of chat dialogues. The model is evaluated on its ability to classify context necessity, demonstrating superior performance over baseline BERT models in terms of accuracy and efficiency. Furthermore, CA-BERT's implementation showcases significant reductions in training time and resource usage, making it feasible for real-time applications. The results indicate that CA-BERT can effectively enhance the functionality of chatbots by providing a nuanced understanding of context, thereby improving user experience and interaction quality in automated systems. This study not only advances the field of NLP in chat applications but also provides a framework for future research into context-sensitive AI developments.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

With the rapid development of natural language processing technology, large language models have demonstrated exceptional performance in various application scenarios. However, training these models requires significant computational resources and data processing capabilities. Cross-cloud federated training offers a new approach to addressing the resource bottlenecks of a single cloud platform, allowing the computational resources of multiple clouds to collaboratively complete the training tasks of large models. This study analyzes the key technologies of cross-cloud federated training, including data partitioning and distribution, communication optimization, model aggregation algorithms, and the compatibility of heterogeneous cloud platforms. Additionally, the study examines data security and privacy protection strategies in cross-cloud training, particularly the application of data encryption and differential privacy techniques. Through experimental validation, the proposed technical framework demonstrates enhanced training efficiency, ensured data security, and reduced training costs, highlighting the broad application prospects of cross-cloud federated training.