Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2608.03148v1
• Date: Tue, 04 Aug 2026 05:26:25 GMT
• Title: Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation
• Abstract summary: We study lightweight RAG chunk selection as an evidence-alignment problem.<n>Our selector combines three complementary feature sources: question hidden states that represent LLM-side query intent, MoE routing-derived expert signals that capture the generator's internal routing structure, and retrieved chunk embeddings that preserve candidate-side evidence geometry.<n>Experiments show that the proposed selector consistently improves rank-1 evidence selection over mobile-applicable baselines by an average of 2.5%.
• Score: 8.227745781139634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: RAG improves the factual grounding of LLM by incorporating external knowledge, but deploying RAG on mobile and edge devices remains challenging because retrieved context increases computation and memory. A direct way to reduce this cost is to retain only one retrieved chunk before generation, but the top-ranked retrieved chunk is not always the most evidence-supporting one, since retrieval similarity does not necessarily imply evidential sufficiency. Existing context-reduction methods can improve context quality, but often require additional LLMs or compressors that are costly under a strict mobile budget. In this paper, we study lightweight RAG chunk selection as an evidence-alignment problem. Our selector combines three complementary feature sources: question hidden states that represent LLM-side query intent, MoE routing-derived expert signals that capture the generator's internal routing structure, and retrieved chunk embeddings that preserve candidate-side evidence geometry. A compact multilayer perceptron maps these features to an evidence prototype in the chunk embedding space, and the candidate most aligned with this prototype is selected by cosine similarity. For stricter deployment budgets, we further introduce an optional task-aware feature selection strategy to reduce the selector input dimension. To support supervised evaluation, we construct semantic chunk-correctness labels based on evidence sufficiency rather than answer-string containment. Experiments show that the proposed selector consistently improves rank-1 evidence selection over mobile-applicable baselines by an average of 2.5%. These results suggest that using LLM-side query representations and MoE routing information and aligning them with retrieval-side candidate embedding is an effective and parameter-efficient strategy for mobile-applicable RAG chunk selection.

Related papers

• Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding [54.840531495584095]
  We propose a dynamic visual selection framework named EviSelect grounded in the target MLLM's internal attention evidence.<n>Our method efficiently approximates maps of the target MLLM using highly compressed visual inputs and sparse attention.<n>EviSelect achieves superior performance compared to existing methods while reducing selected visual tokens by about 50% and achieving a 3.9x end-to-end speedup.
  arXiv  Detail & Related papers  (2026-08-06T09:15:43Z)
• Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors [69.75895255395702]
  Cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generation.<n>A lightweight MLLM selector, even with only 2B parameters, can extract frame-level evidence by converting selected-layer attention into relevance scores through query-conditioned aggregation.<n>Under a 32-frame budget, our selector improves over uniform sampling by up to 6.4 points on Video-MME and outperforms prior training-based selectors under matched frame budgets.
  arXiv  Detail & Related papers  (2026-07-17T07:04:31Z)
• QUBO-Optimized Evidence Selection for Retrieval-Augmented Question Answering with Unconventional Solvers [1.8620637029128544]
  We formulate evidence selection as a Quadratic Unconstrained Binary Optimization problem.<n>Given a question, candidate passages, and information requirements, our method constructs an energy function that balances relevance, requirement coverage, support strength, redundancy, complementarity, and compactness.<n>Low-energy solutions correspond to compact evidence subsets that cover the needed requirements while avoiding unnecessary or repetitive context.
  arXiv  Detail & Related papers  (2026-07-14T04:29:07Z)
• When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents [8.361893760388329]
  Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget.<n>We ask a mechanism question: when does organizing trajectory memory into overlapping semantic units (OSUs) help retrieval over flat or disjoint alternatives?<n>We instantiate this in OSUMem, which retrieves from an overlapping OSU pool via budgeted coarse-to-fine expansion.
  arXiv  Detail & Related papers  (2026-06-19T04:23:04Z)
• Rethinking RAG in Long Videos: What to Retrieve and How to Use It? [56.38819694781005]
  We introduce V-RAGBench, a benchmark of $langle$query, evidence chunk, answer$rangle$ triplets that enables faithful, decoupled evaluation of retrieval and generation.<n>We also present CARVE, a method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk.
  arXiv  Detail & Related papers  (2026-06-11T10:05:49Z)
• Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection [57.3886742625188]
  Pre-Route is a proactive routing framework that performs structured reasoning before answering.<n>Our study shows three key findings: (i) LLMs possess latent routing ability that can be reliably elicited with guidelines; (ii) linear probes reveal that structured prompts sharpen the separability of the "optimal routing" in representation space; and (iii) distillation transfers this reasoning structure to smaller models for lightweight deployment.
  arXiv  Detail & Related papers  (2026-05-11T09:10:55Z)
• Budget-Aware Routing for Long Clinical Text [8.474809035213118]
  Key challenge for large language models is token cost per query and overall deployment cost.<n>We study budgeted context selection, where a subset of document units is chosen under a strict token budget.<n>We propose textbfRCD, a monotone submodular objective that balances relevance, coverage, and diversity.
  arXiv  Detail & Related papers  (2026-05-01T01:34:53Z)
• R$^3$AG: Retriever Routing for Retrieval-Augmented Generation [59.47703698994575]
  R$3$AG decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility.<n>R$3$AG consistently outperforms both the best individual retrievers and state-of-the-art static routing methods.
  arXiv  Detail & Related papers  (2026-04-22T06:51:20Z)
• Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation [110.610512800947]
  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating retrieved information.<n>In RAG, the emphasis has shifted to utility, which considers the usefulness of passages for generating accurate answers.<n>Our approach focuses on utility-based selection rather than ranking, enabling dynamic passage selection tailored to specific queries without the need for fixed thresholds.<n>Our experiments demonstrate that utility-based selection provides a flexible and cost-effective solution for RAG, significantly reducing computational costs while improving answer quality.
  arXiv  Detail & Related papers  (2025-07-25T09:32:29Z)
• Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains [13.58151841630302]
  We propose a novel method METEORA that replaces re-ranking in RAG with a rationale-driven selection approach.<n>We show METEORA improves generation accuracy by 33.34% while using approximately 50% fewer chunks than state-of-the-art re-ranking methods.<n>In adversarial settings, METEORA significantly improves the F1 score from 0.10 to 0.44.
  arXiv  Detail & Related papers  (2025-05-21T20:57:16Z)
• ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems [2.8692611791027893]
  Retrieval-Augmented Generation (RAG) systems generate inaccurate responses due to the retrieval of irrelevant or loosely related information.<n>We propose ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level.
  arXiv  Detail & Related papers  (2024-10-25T14:07:53Z)

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.