# Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement

arXiv: https://arxiv.org/abs/2503.23895 · HTML: https://mlsanity.com/paper/2503.23895/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 30 of 30)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [Physics of Language Models: Part 3.1, Knowledge Storage and Extraction](https://mlsanity.com/paper/2309.14316/) (2023)
- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Physics of Language Models: Part 3.2, Knowledge Manipulation](https://mlsanity.com/paper/2309.14402/) (2023)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer](https://mlsanity.com/paper/2212.02027/) (2022)
- [Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2501.15915/) (2025)
- [With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation](https://mlsanity.com/paper/2401.11504/) (2024)
- [Knowledge Editing through Chain-of-Thought](https://mlsanity.com/paper/2412.17727/) (2024)
- [Uncertainty Estimation in Autoregressive Structured Prediction](https://mlsanity.com/paper/2002.07650/) (2020)
- [Long Context RAG Performance of Large Language Models](https://mlsanity.com/paper/2411.03538/) (2024)
- [To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering](https://mlsanity.com/paper/2403.01924/) (2024)
- [LeKUBE: A Legal Knowledge Update BEnchmark](https://mlsanity.com/paper/2407.14192/) (2024)
- [When Context Leads but Parametric Memory Follows in Large Language Models](https://mlsanity.com/paper/2409.08435/) (2024)
- [MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modality](https://mlsanity.com/paper/2409.04693/) (2024)
- [Evaluating the External and Parametric Knowledge Fusion of Large Language Models](https://mlsanity.com/paper/2405.19010/) (2024)
- [Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering](https://mlsanity.com/paper/2403.15268/) (2024)
- [LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning](https://mlsanity.com/paper/2412.13626/) (2024)

## Built on by (most cited first, 25 of 25)

- [MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models](https://mlsanity.com/paper/2505.22101/) (2025)
- [Skill Retrieval Augmentation for Agentic AI](https://mlsanity.com/paper/2604.24594/) (2026)
- [SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass](https://mlsanity.com/paper/2602.06358/) (2026)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [Understanding LoRA as Knowledge Memory: An Empirical Analysis](https://mlsanity.com/paper/2603.01097/) (2026)
- [NextMem: Towards Latent Factual Memory for LLM-based Agents](https://mlsanity.com/paper/2603.15634/) (2026)
- [Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2602.08382/) (2026)
- [FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG](https://mlsanity.com/paper/2601.05866/) (2026)
- [The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models](https://mlsanity.com/paper/2510.19176/) (2025)
- [Dynamic and Parametric Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.06704/) (2025)
- [Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.19333/) (2025)
- [Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2509.01088/) (2025)
- [HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors](https://mlsanity.com/paper/2601.05587/) (2026)
- [How LoRA Remembers? A Parametric Memory Law for LLM Finetuning](https://mlsanity.com/paper/2605.30260/) (2026)
- [Structure Guided Retrieval-Augmented Generation for Factual Queries](https://mlsanity.com/paper/2604.22843/) (2026)
- [Rethinking LoRA Memory Through the Lens of KV Cache Compression](https://mlsanity.com/paper/2606.05698/) (2026)
- [FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection](https://mlsanity.com/paper/2608.21750/) (2026)
- [GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models](https://mlsanity.com/paper/2511.07457/) (2025)
- [Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2604.26768/) (2026)
- [Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift](https://mlsanity.com/paper/2606.15734/) (2026)
- [MemTools: A Unified Research Framework for Interoperable Agent Memory](https://mlsanity.com/paper/2607.21404/) (2026)
- [A Storage-Retrieval Gap in Parametric Knowledge Graph Memory](https://mlsanity.com/paper/2608.25489/) (2026)
- [CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine](https://mlsanity.com/paper/2609.16301/) (2026)
- [ALLOT: Budgeted Hybrid-Memory Routing for Knowledge Updates in LLMs](https://mlsanity.com/paper/2609.32344/) (2026)
- [Towards In-Parameter Memory Augmentation for Large Language Models](https://mlsanity.com/paper/2610.08630/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it improves reliability by providing factual texts, it significantly increases inference costs as context length grows and introduces challenging issue of RAG hallucination, primarily caused by the lack of corresponding parametric knowledge in LLMs. An efficient solution is to enhance the knowledge of LLMs at test-time. Parametric RAG (PRAG) addresses this by embedding document into LLMs parameters to perform test-time knowledge enhancement, effectively reducing inference costs through offline training. However, its high training and storage costs, along with limited generalization ability, significantly restrict its practical adoption. To address these challenges, we propose Dynamic Parametric RAG (DyPRAG), a novel framework that leverages a lightweight parameter translator model to efficiently convert documents into parametric knowledge. DyPRAG not only reduces inference, training, and storage costs but also dynamically generates parametric knowledge, seamlessly enhancing the knowledge of LLMs and resolving knowledge conflicts in a plug-and-play manner at test-time. Extensive experiments on multiple datasets demonstrate the effectiveness and generalization capabilities of DyPRAG, offering a powerful and practical RAG paradigm which enables superior knowledge fusion and mitigates RAG hallucination in real-world applications. Our code is available at https://github.com/Trae1ounG/DyPRAG.