Quality analysis and evaluation prediction of RAG retrieval based on machine learning algorithms

TL;DR

This paper proposes a machine learning-based approach to evaluate and predict the quality of retrieval modules in RAG systems, aiming to enhance retrieval relevance and overall generation accuracy.

Contribution

It introduces an XGBoost regression model optimized with particle swarm optimization for assessing retrieval quality, addressing limitations in processing tabular features.

Findings

Document relevance significantly impacts answer quality (correlation 0.66).

Tradeoff identified between semantic similarity, redundancy, and diversity.

VMD PSO BiLSTM model outperforms other models with lower error metrics.

Abstract

With the rapid evolution of large language models, retrieval enhanced generation technology has been widely used due to its ability to integrate external knowledge to improve output accuracy. However, the performance of the system is highly dependent on the quality of the retrieval module. If the retrieval results have low relevance to user needs or contain noisy information, it will directly lead to distortion of the generated content. In response to the performance bottleneck of existing models in processing tabular features, this paper proposes an XGBoost machine learning regression model based on feature engineering and particle swarm optimization. Correlation analysis shows that answer_quality is positively correlated with doc_delevance by 0.66, indicating that document relevance has a significant positive effect on answer quality, and improving document relevance may enhance answer quality; The strong negative correlations between semantic similarity, redundancy, and diversity were -0.89 and -0.88, respectively, indicating a tradeoff between semantic similarity, redundancy, and diversity. In other words, as the former two increased, diversity significantly decreased. The experimental results comparing decision trees, AdaBoost, etc. show that the VMD PSO BiLSTM model is superior in all evaluation indicators, with significantly lower MSE, RMSE, MAE, and MAPE compared to the comparison model. The R2 value is higher, indicating that its prediction accuracy, stability, and data interpretation ability are more outstanding. This achievement provides an effective path for optimizing the retrieval quality and improving the generation effect of RAG system, and has important value in promoting the implementation and application of related technologies.