SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems

• URL: http://arxiv.org/abs/2512.12938v1
• Date: Mon, 15 Dec 2025 02:54:10 GMT
• Title: SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems
• Authors: Duy A. Nguyen, Hai H. Do, Minh Doan, Minh N. Do,
• Abstract summary: SPAR (Session-based Pipeline for Adaptive Retrieval) is a conceptual framework that integrates Large Language Models into a Retrieval-Augmented Generation (RAG) architecture specifically designed for legacy enterprise environments.<n>Unlike conventional RAG pipelines, SPAR employs a lightweight two-stage process: a semantic Metadata Index is first created, after which session-specific vector databases are dynamically generated on demand.<n>This design reduces computational overhead while improving transparency, controllability, and relevance in retrieval.
• Score: 6.5637131627375505
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The ability to extract value from historical data is essential for enterprise decision-making. However, much of this information remains inaccessible within large legacy file systems that lack structured organization and semantic indexing, making retrieval and analysis inefficient and error-prone. We introduce SPAR (Session-based Pipeline for Adaptive Retrieval), a conceptual framework that integrates Large Language Models (LLMs) into a Retrieval-Augmented Generation (RAG) architecture specifically designed for legacy enterprise environments. Unlike conventional RAG pipelines, which require costly construction and maintenance of full-scale vector databases that mirror the entire file system, SPAR employs a lightweight two-stage process: a semantic Metadata Index is first created, after which session-specific vector databases are dynamically generated on demand. This design reduces computational overhead while improving transparency, controllability, and relevance in retrieval. We provide a theoretical complexity analysis comparing SPAR with standard LLM-based RAG pipelines, demonstrating its computational advantages. To validate the framework, we apply SPAR to a synthesized enterprise-scale file system containing a large corpus of biomedical literature, showing improvements in both retrieval effectiveness and downstream model accuracy. Finally, we discuss design trade-offs and outline open challenges for deploying SPAR across diverse enterprise settings.

Related papers

• UniPAR: A Unified Framework for Pedestrian Attribute Recognition [14.613498516126498]
  We propose UniPAR, a unified Transformer-based framework for Pedestrian Attribute Recognition.<n>By incorporating a unified data scheduling strategy and a dynamic classification head, UniPAR enables a single model to simultaneously process diverse datasets.<n> Experimental results on the widely used benchmark datasets, including MSP60K, DukeMTMC, and EventPAR, demonstrate that UniPAR achieves performance comparable to specialized SOTA methods.
  arXiv  Detail & Related papers  (2026-03-05T12:34:35Z)
• Relatron: Automating Relational Machine Learning over Relational Databases [50.94254514286021]
  We present a study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks.<n>Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and accuracy is an unreliable guide for choice architecture.
  arXiv  Detail & Related papers  (2026-02-26T02:45:22Z)
• Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration [14.88759517020146]
  Existing RAG pipelines incur substantial retrieval and generation overhead when applied to large-scale entity matching.<n>We introduce CE-RAG4EM, a cost-efficient RAG architecture that reduces computation through blocking-based batch retrieval and generation.
  arXiv  Detail & Related papers  (2026-02-05T14:33:00Z)
• Bridging OLAP and RAG: A Multidimensional Approach to the Design of Corpus Partitioning [0.3437656066916039]
  We propose a conceptual framework to guide the design of multidimensional partitions for RAG corpora.<n>The framework naturally supports hierarchical routing and controlled fallback strategies, ensuring that retrieval remains robust even in the presence of incomplete metadata.
  arXiv  Detail & Related papers  (2026-01-07T09:37:36Z)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval [11.72564658353791]
  Dense retrieval has become the industry standard in large-scale information retrieval systems due to its high efficiency and competitive accuracy.<n>The widely adopted dual-tower encoding architecture introduces inherent challenges, primarily representational space misalignment and retrieval index inconsistency.<n>This paper proposes a simple and effective framework named SCI comprising two synergistic modules.<n>We provide theoretical guarantees for our approach, with its effectiveness validated by results across public datasets and real-world e-commerce datasets.
  arXiv  Detail & Related papers  (2025-12-15T08:11:24Z)
• URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding [55.45331924836242]
  We present URaG, a framework that Unifies Retrieval and Generation within a single MLLM.<n>We show that URaG achieves state-of-the-art performance while reducing computational overhead by 44-56%.
  arXiv  Detail & Related papers  (2025-11-13T17:54:09Z)
• Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering [0.0]
  We introduce a sophisticated indexing pipeline to create contextually rich document chunks.<n>We benchmark a spectrum of enhancements, including pre-retrieval filtering, post-retrieval reranking, and enriched embeddings.<n>Our proposed optimal architecture combines LLM-driven pre-retrieval optimizations with these contextual embeddings to achieve superior performance.
  arXiv  Detail & Related papers  (2025-10-28T13:16:36Z)
• REFRAG: Rethinking RAG based Decoding [67.4862300145604]
  REFRAG is an efficient decoding framework that compresses, senses, and expands to improve latency in RAG applications.<n>We provide rigorous validation of REFRAG across diverse long-context tasks, including RAG, multi-turn conversations, and long document summarization.
  arXiv  Detail & Related papers  (2025-09-01T03:31:44Z)
• SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search [2.8085728901059848]
  We introduce SPAR, a multi-agent framework that incorporates RefChain-based query decomposition and query evolution.<n>We also construct SPARBench, a challenging benchmark with expert-annotated relevance labels.<n> Experimental results demonstrate that SPAR substantially outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-07-21T05:06:53Z)
• Leveraging Machine Learning and Enhanced Parallelism Detection for BPMN Model Generation from Text [75.77648333476776]
  This paper introduces an automated pipeline for extracting BPMN models from text.<n>A key contribution of this work is the introduction of a newly annotated dataset.<n>We augment the dataset with 15 newly annotated documents containing 32 parallel gateways for model training.
  arXiv  Detail & Related papers  (2025-07-11T07:25:55Z)
• eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing [6.450269621190948]
  We introduce eSapiens, a unified question-answering system designed for enterprise settings.<n>eSapiens bridges structured databases and unstructured corpora via a dual-module architecture.<n>We evaluate eSapiens on the RAGTruth benchmark, analyzing performance across key dimensions such as completeness, hallucination, and context utilization.
  arXiv  Detail & Related papers  (2025-06-20T06:07:20Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• Augmented Knowledge Graph Querying leveraging LLMs [2.5311562666866494]
  We introduce SparqLLM, a framework that enhances the querying of Knowledge Graphs (KGs)<n>SparqLLM executes the Extract, Transform, and Load (ETL) pipeline to construct KGs from raw data.<n>It also features a natural language interface powered by Large Language Models (LLMs) to enable automatic SPARQL query generation.
  arXiv  Detail & Related papers  (2025-02-03T12:18:39Z)

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.