Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909595826388992 |
|---|---|
| author | He, Jacky Liu, Guiran Zhu, Binrong Zhang, Hanlu Zheng, Hongye Wang, Xiaokai |
| author_facet | He, Jacky Liu, Guiran Zhu, Binrong Zhang, Hanlu Zheng, Hongye Wang, Xiaokai |
| contents | This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency in large language models for open-domain question answering and complex generation tasks. The method introduces a multi-level perceptive retrieval vector construction strategy and a differentiable document matching path. These components enable end-to-end joint training and collaborative optimization of the retrieval and generation modules. This effectively addresses the limitations of static RAG structures in context adaptation and knowledge access. Experiments are conducted on the Natural Questions dataset. The proposed structure is thoroughly evaluated across different large models, including GPT-4, GPT-4o, and DeepSeek. Comparative and ablation experiments from multiple perspectives confirm the significant improvements in BLEU and ROUGE-L scores. The approach also demonstrates stronger robustness and generation consistency in tasks involving semantic ambiguity and multi-document fusion. These results highlight its broad application potential and practical value in building high-quality language generation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19436 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models He, Jacky Liu, Guiran Zhu, Binrong Zhang, Hanlu Zheng, Hongye Wang, Xiaokai Computation and Language Machine Learning This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency in large language models for open-domain question answering and complex generation tasks. The method introduces a multi-level perceptive retrieval vector construction strategy and a differentiable document matching path. These components enable end-to-end joint training and collaborative optimization of the retrieval and generation modules. This effectively addresses the limitations of static RAG structures in context adaptation and knowledge access. Experiments are conducted on the Natural Questions dataset. The proposed structure is thoroughly evaluated across different large models, including GPT-4, GPT-4o, and DeepSeek. Comparative and ablation experiments from multiple perspectives confirm the significant improvements in BLEU and ROUGE-L scores. The approach also demonstrates stronger robustness and generation consistency in tasks involving semantic ambiguity and multi-document fusion. These results highlight its broad application potential and practical value in building high-quality language generation systems. |
| title | Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2504.19436 |