mlsanityData to 7 Oct 2026

AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM

arXiv 2510.17934 ↗First posted 20 Oct 2025cs.CL cs.AIcited by 1

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-augmented generation (RAG) has shown some success in augmenting large language models (LLMs) with external knowledge. However, as a non-parametric knowledge integration paradigm for LLMs, RAG methods heavily rely on external retrieval modules and the retrieved textual context prior. Especially for very large scale knowledge augmentation, they would introduce substantial inference latency due to expensive searches and much longer relevant context. In this paper, we propose a parametric knowledge integration method, called AtlasKV, a scalable, effective, and general way to augment LLMs with billion-scale knowledge graphs (KGs) (e.g. 1B triples) using very little GPU memory cost (e.g. less than 20GB VRAM). In AtlasKV, we introduce KG2KV and HiKVP to integrate KG triples into LLMs at scale with sub-linear time and memory complexity. It maintains strong knowledge grounding and generalization performance using the LLMs' inherent attention mechanism, and requires no external retrievers, long context priors, or retraining when adapting to new knowledge.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 51 of its 59 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

51 of 59 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models10 May
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  3. 2023Ragas: Automated Evaluation of Retrieval Augmented Generation26 Sep

Other references · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2024GPT-4o System Cardcited by 4,467
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  9. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  10. 2019Language Models as Knowledge Bases?cited by 1,922
  11. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  12. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
36 more
  1. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  2. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  3. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  4. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  5. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  6. 2019How Can We Know What Language Models Know?cited by 953
  7. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  8. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  9. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  10. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  11. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  12. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 240
  13. 2021On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptationcited by 147
  14. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  15. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  16. 2024RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generationcited by 97
  17. 2021Efficient Nearest Neighbor Language Modelscited by 93
  18. 2019ASER: A Large-scale Eventuality Knowledge Graphcited by 89
  19. 2025How much do language models memorize?cited by 53
  20. 2025KGGen: Extracting Knowledge Graphs from Plain Text with Language Modelscited by 49
  21. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 47
  22. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 46
  23. 2024Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Taskscited by 38
  24. 2020Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledgecited by 37
  25. 2023Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memoriescited by 34
  26. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 30
  27. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  28. 2024SiReRAG: Indexing Similar and Related Information for Multihop Reasoningcited by 23
  29. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  30. 2024KBLaM: Knowledge Base augmented Language Modelcited by 16
  31. 2025Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Modelscited by 16
  32. 2025LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrievalcited by 14
  33. 2024Can LLMs be Good Graph Judge for Knowledge Graph Construction?cited by 11
  34. 2024Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generationcited by 8
  35. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQAcited by 7
  36. 2025GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention
  2. 2026Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
  3. 2025RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
  4. 2024KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models
  5. 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
  6. 2025GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
  7. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  8. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models