mlsanityData to 14 Oct 2026

Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models

arXiv 2504.19436 ↗First posted 28 Apr 2025cs.CL cs.LGcited by 8

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 23 references that are in the map. First posted on arXiv 28 Apr 2025.

Builds on

9 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering11 Jun

Other references · 8

  1. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  2. 2024Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networkscited by 33
  3. 2024Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systemscited by 15
  4. 2025Social Network User Profiling for Anomaly Detection Based on Graph Neural Networkscited by 9
  5. 2024Retrieval Augmented Generation for Dynamic Graph Modelingcited by 6
  6. 2025Context-Aware Adaptive Sampling for Intelligent Data Acquisition Systems Using DQNcited by 6
  7. 2024DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAGcited by 4
  8. 2025Improving Harmful Text Detection with Joint Retrieval and External Knowledgecited by 2

Built on by

Cited by year

Citing papers per year: 2025: 8.

8 papers.

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025Structured Memory Mechanisms for Stable Context Representation in Large Language Modelscited by 9
  3. 2025Deep Probabilistic Modeling of User Behavior for Anomaly Detection via Mixture Density Networkscited by 6
  4. 2025Collaborative Distillation Strategies for Parameter-Efficient Language Model Deploymentcited by 5
  5. 2025Time-Series Learning for Proactive Fault Prediction in Distributed Systems with Deep Neural Structurescited by 4
  6. 2025BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channelcited by 3
  7. 2025Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answeringcited by 1
  8. 2025Interpretability Framework for LLMs in Undergraduate Calculuscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  2. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  3. 2025MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework
  4. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  5. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  6. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
  7. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  8. 2025Dynamic and Parametric Retrieval-Augmented Generation