A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2604.14403v1
• Date: Wed, 15 Apr 2026 20:34:10 GMT
• Title: A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
• Abstract summary: We propose a unified model that compresses the RAG context and utilizes the same representations for retrieval.<n>With an average of 1/10 of the context, our model matches the performance of a traditional RAG reader without increasing storage requirements.
• Score: 31.59984397397994
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces local hardware constraints, it introduces significant drawbacks: privacy concerns regarding data access, recurring maintenance and storage costs, increased latency, and the necessity of an internet connection. On-device RAG addresses these challenges by executing the entire pipeline locally, making it ideal for querying sensitive personal information such as financial documents, contact details, and medical history. However, on-device deployment necessitates a delicate balance between limited memory and disk space. Specifically, the context size provided to the generative model must be restricted to manage KV cache and attention memory usage, while the size of stored embeddings must be minimized to preserve disk space. In this work, we propose a unified model that compresses the RAG context and utilizes the same representations for retrieval. This approach minimizes disk utilization compared to using separate representations, while significantly reducing the context size required for generation. With an average of 1/10 of the context, our model matches the performance of a traditional RAG reader without increasing storage requirements compared to a multi-vector retrieval model. This approach represents the first model to unify retrieval and context compression using a shared model and representation. We believe this work will inspire further consolidation of distinct models to optimize on-device performance.

Related papers

• Collaborative Memory Augmentation for Generative Recommendation [49.76630658239287]
  We propose textbfOMEGA, a cOllaborative MEmory augmentation framework for Generative recommendAtion.<n>We first introduce a latent context compression method that utilizes learnable query tokens to distill sequential user behavior into compact representations.<n>These compressed representations are aggregated into a collaborative memory bank, serving as an explicit repository of global behavioral patterns.
  arXiv  Detail & Related papers  (2026-08-02T15:34:43Z)
• Comparative Characterization of KV Cache Management Strategies for LLM Inference [0.31498833540989407]
  Key-Value caches are essential for Efficient inference with Large Language Models (LLMs)<n>These caches are essential to minimize redundant computation during autoregressive token generation.<n>The growth of KV caches has posed significant system-level challenges.
  arXiv  Detail & Related papers  (2026-04-06T16:00:39Z)
• Clustering-driven Memory Compression for On-device Large Language Models [36.84681161552071]
  We introduce a memory compression strategy that balances context efficiency and personalization quality.<n>Our method groups memories by similarity and merges them within clusters prior to concatenation.<n>Experiments demonstrate that our approach substantially lowers the number of memory tokens while outperforming baseline strategies.
  arXiv  Detail & Related papers  (2026-01-24T12:31:15Z)
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension [77.93156509994994]
  We show how to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.<n>Existing embedding models are not well-equipped to encode such situated context effectively.<n>Our method substantially outperforms state-of-the-art embedding models.
  arXiv  Detail & Related papers  (2025-08-03T23:59:31Z)
• ImpRAG: Retrieval-Augmented Generation with Implicit Queries [34.72864597562907]
  ImpRAG is a query-free RAG system that integrates retrieval and generation into a unified model.<n>We show that ImpRAG achieves 3.6-11.5 improvements in exact match scores on unseen tasks with diverse formats.
  arXiv  Detail & Related papers  (2025-06-02T21:38:21Z)
• Runtime Adaptive Pruning for LLM Inference [7.5252252615137225]
  We propose RAP, an elastic pruning framework driven by reinforcement learning (RL)<n>RAP tracks the evolving ratio between model parameters and KV-cache across practical execution.<n>RAP outperforms state-of-the-art baselines, marking the first time to jointly consider model weights and KVcache on the fly.
  arXiv  Detail & Related papers  (2025-05-22T06:12:42Z)
• Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance [34.695803671702606]
  Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance.<n>Retrieval-augmented generation (RAG) is a promising solution to enhance model performance by integrating external databases, without requiring intensive on-device model retraining.<n>We propose DRAGON, a distributed RAG framework to enhance on-device SLMs through both general and personal knowledge without the risk of leaking document privacy.
  arXiv  Detail & Related papers  (2025-04-15T13:53:08Z)
• Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models [51.3915762595891]
  This paper presents an efficient LoRA-based personalization approach for on-device subject-driven generation. Our method, termed Hollowed Net, enhances memory efficiency during fine-tuning by modifying the architecture of a diffusion U-Net.
  arXiv  Detail & Related papers  (2024-11-02T08:42:48Z)
• xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token [108.7069350303884]
  xRAG is an innovative context compression method tailored for retrieval-augmented generation.<n>xRAG seamlessly integrates document embeddings into the language model representation space.<n> Experimental results demonstrate that xRAG achieves an average improvement of over 10% across six knowledge-intensive tasks.
  arXiv  Detail & Related papers  (2024-05-22T16:15:17Z)
• CORM: Cache Optimization with Recent Message for Large Language Model Inference [57.109354287786154]
  We introduce an innovative method for optimizing the KV cache, which considerably minimizes its memory footprint. CORM, a KV cache eviction policy, dynamically retains essential key-value pairs for inference without the need for model fine-tuning. Our validation shows that CORM reduces the inference memory usage of KV cache by up to 70% with negligible performance degradation across six tasks in LongBench.
  arXiv  Detail & Related papers  (2024-04-24T16:11:54Z)
• Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks [65.3963282551994]
  We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy.
  arXiv  Detail & Related papers  (2020-10-06T15:16:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.