Keywords
Natural language processing
Deep learning
Baidu Qianfan large model platform
Supervised fine-tuning
Model training and evaluation
Submitted : 2024-10-28
Accepted : 2024-11-12
Published : 2024-11-27
Abstract
Leveraging the Baidu Qianfan model platform, this paper designs and implements a highly efficient and accurate scoring system for subjective questions, focusing primarily on questions in the field of computer network technology. The system enhances the foundational model by utilizing Qianfan’s training tools and integrating advanced techniques, such as supervised fine-tuning. In the data preparation phase, a comprehensive collection of subjective data related to computer network technology is gathered, cleaned, and labeled. During model training and evaluation, optimal hyperparameters and tuning strategies are applied, resulting in a model capable of scoring with high accuracy. Evaluation results demonstrate that the proposed model performs well across multiple dimensions—content, expression, and development scores—yielding results comparable to those of manual scoring.
References
Xiao L, Liu J, 2021, Combination of Subjective Item Grading Method Based on Similarity Research. Journal of Guizhou University: Natural Science Edition, 38(05): 64–68.
Li Y, 2023, Big Model Reshapes Digital World. New Security, (06): 24–26.
Zhang L, Zhang S, 2012, The Subjective Topic Grading Algorithm Based on Semantic Similarity Research. Journal of Hebei University of Science and Technology, 33(03): 263–265.
Xu Z, 2021, Research on Short Text Subjective Question Scoring Review Algorithm and System Implementation, dissertation, Zhongran University of Economics and Law.
Zhou Z, 2023, From Baidu AI Painting, the Future Reform Behind the Tiangong Feast Screen Video. Big Data Era, 2023(2): 54–59.
Wang S, Gong J, Wang Y, et al., 2023, Key Points Matching Based Scoring Method for Liberal Arts Subjective Questions. Journal of Chinese Information Processing, 37(6): 165–178.
Yang J, 2018, Application of Machine Learning Algorithm in Data Mining. Electronic Technology and Software Engineering, (04): 191.
Nan X, 2016, Automatic Scoring System of Subjective Questions Based on Sentence Similarity. Silk Road Vision, 2016(28): 54–57.
Chen F, Yang Q, 2015, On the Related Technology of Data Integration. Science and Technology Information, 13(08): 30.
Huang Q, 2018, Jiangxi Examination Prose Reading Subjective Item Grading Standard Research. Journal of Literature Education, 2018(3): 3.
Wang X, Fu X, 2023, The Application Trend of Artificial Intelligence Technology in the Era of Big Model—Taking the Big Model of Cloud Slave Technology as an Example. China Security and Defense, 2023(12): 53–58.
Huang C, Li H, Qi X, 2022, Design of a Small Program for Subjective Question Scoring Based on Natural Language Processing. Wen Yuan (High School Edition), 2022(2): 199–201.
Yao X, 2021, An Improved KMP Algorithm and Its Application in the Subjective Topic Grading. Journal of Network Security Technology and Application, (06): 27–29.
Hu Y, 2024, Big Models Accelerate the Release of AI Potential. Outlook, 2024(3): 60–61.
Zhang F, Han L, 2024, Research on Application of Generative Artificial Intelligence Based on Large Model in Audit Practice. Internal Auditing in China, (08): 42–48.