mlsanityData to 7 Oct 2026

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

arXiv 2512.12938 ↗First posted 15 Dec 2025cs.IRcited by 0

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

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 38 of its 55 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

38 of 55 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs28 Aug
  2. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions3 Oct
  3. 2024RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation15 Aug
  4. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers22 Mar
  5. 2024Bridging the Preference Gap between Retrievers and LLMs13 Jan
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2025Qwen2.5-VL Technical Reportcited by 5,418
  7. 2017Billion-scale similarity search with GPUscited by 2,477
  8. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  9. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  10. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  11. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  12. 2023Recommender Systems with Generative Retrievalcited by 191
20 more
  1. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  2. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  3. 2017Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graphcited by 103
  4. 2024CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answeringcited by 70
  5. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 61
  6. 2024AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Frameworkcited by 47
  7. 2022PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extractioncited by 19
  8. 2020TNT-KID: Transformer-based Neural Tagger for Keyword Identificationcited by 15
  9. 2023TagGPT: Large Language Models are Zero-shot Multimodal Taggerscited by 15
  10. 2023IAG: Induction-Augmented Generation Framework for Answering Reasoning Questionscited by 15
  11. 2023LLM-TAKE: Theme Aware Keyword Extraction Using Large Language Modelscited by 8
  12. 2024RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenancecited by 7
  13. 2025QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performancecited by 6
  14. 2025RL-based Query Rewriting with Distilled LLM for online E-Commerce Systemscited by 5
  15. 2025RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedbackcited by 5
  16. 2024Agentic AI-Driven Technical Troubleshooting for Enterprise Systems: A Novel Weighted Retrieval-Augmented Generation Paradigmcited by 4
  17. 2025Multimodal Medical Image Binding via Shared Text Embeddingscited by 3
  18. 2025LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Modelscited by 2
  19. 2025Improving the Accuracy and Efficiency of Legal Document Tagging with Large Language Models and Instruction Promptscited by 2
  20. 2025eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  2. 2025REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing
  3. 2025Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models
  4. 2025Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG
  5. 2026M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation
  6. 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
  7. 2026REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
  8. 2025MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG