mlsanityData to 7 Oct 2026

MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation

arXiv 2407.01972 ↗First posted 2 Jul 2024cs.IR cs.AI cs.HCcited by 12

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

Abstract (arXiv)

Retrieval-augmented text generation (RAG) addresses the common limitations of large language models (LLMs), such as hallucination, by retrieving information from an updatable external knowledge base. However, existing approaches often require dedicated backend servers for data storage and retrieval, thereby limiting their applicability in use cases that require strict data privacy, such as personal finance, education, and medicine. To address the pressing need for client-side dense retrieval, we introduce MeMemo, the first open-source JavaScript toolkit that adapts the state-of-the-art approximate nearest neighbor search technique HNSW to browser environments. Developed with modern and native Web technologies, such as IndexedDB and Web Workers, our toolkit leverages client-side hardware capabilities to enable researchers and developers to efficiently search through millions of high-dimensional vectors in the browser. MeMemo enables exciting new design and research opportunities, such as private and personalized content creation and interactive prototyping, as demonstrated in our example application RAG Playground. Reflecting on our work, we discuss the opportunities and challenges for on-device dense retrieval. MeMemo is available at https://github.com/poloclub/mememo.

Key facts. Cited by 12 papers 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 33 of its 72 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

33 of 72 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024The Power of Noise: Redefining Retrieval for RAG Systems26 Jan

Other references · 32

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  7. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  8. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  9. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 525
  10. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  11. 2023Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMscited by 175
  12. 2022DocPrompting: Generating Code by Retrieving the Docscited by 151
20 more
  1. 2024RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculturecited by 80
  2. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  3. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usagecited by 54
  4. 2020EdgeRec: Recommender System on Edge in Mobile Taobaocited by 29
  5. 2023WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddingscited by 28
  6. 2023Opportunities for Retrieval and Tool Augmented Large Language Models in Scientific Facilitiescited by 27
  7. 2021Passage Retrieval for Outside-Knowledge Visual Question Answeringcited by 25
  8. 2022Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Valuescited by 25
  9. 2023CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programmingcited by 16
  10. 2023Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspectivecited by 16
  11. 2021Amortized Neural Networks for Low-Latency Speech Recognitioncited by 9
  12. 2023GAM Coach: Towards Interactive and User-centered Algorithmic Recoursecited by 9
  13. 2023Gender, Age, and Technology Education Influence the Adoption and Appropriation of LLMscited by 9
  14. 2024Wordflow: Social Prompt Engineering for Large Language Modelscited by 9
  15. 2022Efficient On-Device Session-Based Recommendationcited by 8
  16. 2023Adapting LLMs for Efficient, Personalized Information Retrieval: Methods and Implicationscited by 8
  17. 2023GPU-based Private Information Retrieval for On-Device Machine Learning Inferencecited by 5
  18. 2023WebSHAP: Towards Explaining Any Machine Learning Models Anywherecited by 2
  19. 2021Learning a Neural Diff for Speech Modelscited by 1
  20. 2022DocuT5: Seq2seq SQL Generation with Table Documentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 4.

12 papers.

  1. 2025A Survey of Personalization: From RAG to Agentcited by 26
  2. 2025TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrievalcited by 9
  3. 2025MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAGcited by 9
  4. 2025EnronQA: Towards Personalized RAG over Private Documentscited by 8
  5. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systemscited by 7
  6. 2025LEANN: A Low-Storage Vector Indexcited by 4
  7. 2025Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Executioncited by 4
  8. 2025WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browserscited by 1
  9. 2025On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwardingcited by 1
  10. 2026TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUscited by 0
  11. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systemscited by 0
  12. 2026As We May Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
  2. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
  3. 2025MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
  4. 2025Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
  5. 2025Assessing RAG and HyDE on 1B vs. 4B-Parameter Gemma LLMs for Personal Assistants Integretion
  6. 2026RAGe: A Retrieval-Augmented Generation Evaluation Framework
  7. 2025Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems
  8. 2024HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems