mlsanityData to 14 Oct 2026

CiMRAG: CiM-Aware Domain-Adaptive and Noise-Resilient Retrieval-Augmented Generation for Edge-Based LLMs

arXiv 2601.20041 ↗First posted 27 Jan 2026cs.LG cs.AIcited by 0

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

Abstract (arXiv)

Personalized virtual assistants powered by large language models (LLMs) on edge devices are attracting growing attention, with Retrieval-Augmented Generation (RAG) emerging as a key method for personalization by retrieving relevant profile data and generating tailored responses. However, deploying RAG on edge devices faces efficiency hurdles due to the rapid growth of profile data, such as user-LLM interactions and recent updates. While Computing-in-Memory (CiM) architectures mitigate this bottleneck by eliminating data movement between memory and processing units via in-situ operations, they are susceptible to environmental noise that can degrade retrieval precision. This poses a critical issue in dynamic, multi-domain edge-based scenarios (e.g., travel, medicine, and law) where both accuracy and adaptability are paramount. To address these challenges, we propose Task-Oriented Noise-resilient Embedding Learning (TONEL), a framework that improves noise robustness and domain adaptability for RAG in noisy edge environments. TONEL employs a noise-aware projection model to learn task-specific embeddings compatible with CiM hardware constraints, enabling accurate retrieval under noisy conditions. Extensive experiments conducted on personalization benchmarks demonstrate the effectiveness and practicality of our methods relative to strong baselines, especially in task-specific noisy scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 25 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

19 of 25 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models10 May
  2. 2024Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures7 May

Other references · 17

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  4. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  5. 2024Large Language Models: A Surveycited by 525
  6. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  7. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
  8. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 210
  9. 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 128
  10. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
  11. 2024On-Device Language Models: A Comprehensive Reviewcited by 104
  12. 2024A Review on Edge Large Language Models: Design, Execution, and Applicationscited by 100
5 more
  1. 2019Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Acceleratorscited by 32
  2. 2021Uncertainty Modeling of Emerging Device-based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Searchcited by 17
  3. 2024Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devicescited by 17
  4. 2022SWIM: Selective Write-Verify for Computing-in-Memory Neural Acceleratorscited by 16
  5. 2023Compute-in-Memory based Neural Network Accelerators for Safety-Critical Systems: Worst-Case Scenarios and Protectionscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Device
  2. 2025Adaptive Contextual Caching for Mobile Edge Large Language Model Service ↗
  3. 2025Tuning LLMs by RAG Principles: Towards LLM-native Memory
  4. 2024EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting
  5. 2025LLM-Independent Adaptive RAG: Let the Question Speak for Itself
  6. 2024EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update
  7. 2025EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices
  8. 2026CQ-CiM: Hardware-Aware Embedding Shaping for Robust CiM-Based Retrieval