Research on Intelligent Evaluation Model Based on Large Models

Peihong Wang, Wei Chen, Zehua Wang, Tingting Xu, Jueting Liu

Abstract: With the rapid development of artificial intelligence technology, the intelligent evaluation model based on large models has gradually become an important innovation for optimizing traditional evaluation processes. This study aims to design and implement an intelligent evaluation model leveraging large models to improve fairness, efficiency, and accuracy in the evaluation process through deep learning-based modeling and intelligent analysis of evaluation data. The study employed Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) for model training and evaluation. Experimental results showed that GBDT outperformed SVM and MLP in key metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), highlighting its superior capability in handling complex, multidimensional evaluation tasks. These results validate the effectiveness and reliability of the proposed model, with an in-depth discussion of its advantages, limitations, and future applications. This paper systematically explains large model technology and its potential applications in evaluation, constructing an intelligent evaluation framework that covers key steps such as data collection, preprocessing, and model training, this study provides theoretical and practical support for the future development and application of intelligent evaluation systems.

External IDs:dblp:conf/icic/WangCWXL25