# Parametric Retrieval Augmented Generation

arXiv: https://arxiv.org/abs/2501.15915 · HTML: https://mlsanity.com/paper/2501.15915/

## Key facts

- Cited by 38 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 33 of its 54 references that are in the map.
- First posted on arXiv 27 Jan 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 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [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)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Physics of Language Models: Part 3.1, Knowledge Storage and Extraction](https://mlsanity.com/paper/2309.14316/) (2023)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [Neuron-Level Knowledge Attribution in Large Language Models](https://mlsanity.com/paper/2312.12141/) (2023)
- [Scaling Laws For Dense Retrieval](https://mlsanity.com/paper/2403.18684/) (2024)
- [Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval](https://mlsanity.com/paper/2410.13339/) (2024)
- [Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.00175/) (2024)
- [Mitigating Entity-Level Hallucination in Large Language Models](https://mlsanity.com/paper/2407.09417/) (2024)
- [Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval](https://mlsanity.com/paper/2312.10661/) (2023)
- [THUIR2 at NTCIR-16 Session Search (SS) Task](https://mlsanity.com/paper/2307.00250/) (2023)

## Built on by (most cited first, 30 of 38)

- [MemGen: Weaving Generative Latent Memory for Self-Evolving Agents](https://mlsanity.com/paper/2509.24704/) (2025)
- [Cartridges: Lightweight and general-purpose long context representations via self-study](https://mlsanity.com/paper/2506.06266/) (2025)
- [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)
- [A Survey on Knowledge-Oriented Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10677/) (2025)
- [Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement](https://mlsanity.com/paper/2503.23895/) (2025)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [ORANSight-2.0: Foundational LLMs for O-RAN](https://mlsanity.com/paper/2503.05200/) (2025)
- [Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing](https://mlsanity.com/paper/2506.00536/) (2025)
- [Understanding LoRA as Knowledge Memory: An Empirical Analysis](https://mlsanity.com/paper/2603.01097/) (2026)
- [RARE: Retrieval-Augmented Reasoning Modeling](https://mlsanity.com/paper/2503.23513/) (2025)
- [OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG](https://mlsanity.com/paper/2601.09028/) (2026)
- [ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval](https://mlsanity.com/paper/2511.06202/) (2025)
- [PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training](https://mlsanity.com/paper/2602.13840/) (2026)
- [Revisiting Text Ranking in Deep Research](https://mlsanity.com/paper/2602.21456/) (2026)
- [Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding](https://mlsanity.com/paper/2504.01281/) (2025)
- [Dynamic and Parametric Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.06704/) (2025)
- [ReasonCACHE: Teaching LLMs To Reason Without Weight Updates](https://mlsanity.com/paper/2602.02366/) (2026)
- [Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents](https://mlsanity.com/paper/2604.27283/) (2026)
- [User as Engram: Internalizing Per-User Memory as Local Parametric Edits](https://mlsanity.com/paper/2606.19172/) (2026)
- [SINDI: An Efficient Index for Sparse Vector Approximate Maximum Inner Product Search](https://mlsanity.com/paper/2509.08395/) (2025)
- [A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation](https://mlsanity.com/paper/2601.22708/) (2026)
- [FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters](https://mlsanity.com/paper/2602.05235/) (2026)
- [Parametric Social Identity Injection and Diversification in Public Opinion Simulation](https://mlsanity.com/paper/2603.16142/) (2026)
- [Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories](https://mlsanity.com/paper/2606.03979/) (2026)
- [GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models](https://mlsanity.com/paper/2511.07457/) (2025)
- [Analytical Search](https://mlsanity.com/paper/2602.11581/) (2026)
- [CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.25182/) (2026)
- [Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.01302/) (2026)
- [On the Persistent Effects of Lexicality in Large Language Models](https://mlsanity.com/paper/2606.02750/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In particular, existing RAG methods append relevant documents retrieved from external corpus or databases to the input of LLMs to guide their generation process, which we refer to as the in-context knowledge injection method. While this approach is simple and often effective, it has inherent limitations. Firstly, increasing the context length and number of relevant documents can lead to higher computational overhead and degraded performance, especially in complex reasoning tasks. More importantly, in-context knowledge injection operates primarily at the input level, but LLMs store their internal knowledge in their parameters. This gap fundamentally limits the capacity of in-context methods. To this end, we introduce Parametric retrieval-augmented generation (Parametric RAG), a new RAG paradigm that integrates external knowledge directly into the parameters of feed-forward networks (FFN) of an LLM through document parameterization. This approach not only saves online computational costs by eliminating the need to inject multiple documents into the LLMs' input context, but also deepens the integration of external knowledge into the parametric knowledge space of the LLM. Experimental results demonstrate that Parametric RAG substantially enhances both the effectiveness and efficiency of knowledge augmentation in LLMs. Also, it can be combined with in-context RAG methods to achieve even better performance. We have open-sourced all the code, data, and models in the following anonymized GitHub link: https://github.com/oneal2000/PRAG