arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.20041cs.LGcs.AI
收藏

CiMRAG: 面向边缘LLM的意识域自适应与噪声鲁棒检索增强生成

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

National Taiwan University(国立台湾大学)

Shih-Hsuan Chiu, Ming-Syan Chen

AI总结:

CiMRAG通过TONEL框架提升边缘LLM在噪声环境下的检索准确性和域适应性。

摘要:

基于大型语言模型(LLMs)的个性化虚拟助手在边缘设备上日益受到关注,检索增强生成(RAG)作为个性化的关键方法,通过检索相关资料并生成定制响应。然而,部署RAG在边缘设备面临效率难题,由于用户-LLM交互和最近更新等资料的快速增长。虽然计算在内存(CiM)架构通过在 situ 操作消除了内存与处理单元之间的数据移动瓶颈,但其易受环境噪声影响,可能导致检索精度下降。这在动态、多域边缘场景(如旅行、医学和法律)中尤为关键,因为准确性和适应性至关重要。为了解决这些挑战,我们提出了面向任务的噪声鲁棒嵌入学习(TONEL)框架,该框架改进了RAG在噪声边缘环境中的噪声鲁棒性和域适应性。TONEL采用噪声意识的投影模型,学习任务特定的嵌入,以适应CiM硬件约束,从而在噪声条件下实现准确检索。在个性化基准上的广泛实验表明,我们的方法相对于强大的基线在任务特定的噪声场景中表现出色。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑