mlsanityData to 14 Oct 2026

LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints

arXiv 2510.27054 ↗First posted 30 Oct 2025cs.CLcited by 3

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

Abstract (arXiv)

This paper addresses the issues of insufficient coverage, unstable results, and limited reliability in retrieval-augmented generation under complex knowledge environments, and proposes a confidence control method that integrates multi-granularity memory indexing with uncertainty estimation. The method builds a hierarchical memory structure that divides knowledge representations into different levels of granularity, enabling dynamic indexing and retrieval from local details to global context, and thus establishing closer semantic connections between retrieval and generation. On this basis, an uncertainty estimation mechanism is introduced to explicitly constrain and filter low-confidence paths during the generation process, allowing the model to maintain information coverage while effectively suppressing noise and false content. The overall optimization objective consists of generation loss, entropy constraints, and variance regularization, forming a unified confidence control framework. In the experiments, comprehensive sensitivity tests and comparative analyses were designed, covering hyperparameters, environmental conditions, and data structures, to verify the stability and robustness of the proposed method across different scenarios. The results show that the method achieves superior performance over existing models in QA accuracy, retrieval recall, ranking quality, and factual consistency, demonstrating the effectiveness of combining multi-granularity indexing with confidence control. This study not only provides a new technical pathway for retrieval-augmented generation but also offers practical evidence for improving the reliability and controllability of large models in complex contexts.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 31 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

15 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey21 Apr
  2. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity16 Oct

Other references · 13

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  2. 2024UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generationcited by 16
  3. 2025Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysiscited by 14
  4. 2025Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Modelscited by 10
  5. 2025Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generationcited by 9
  6. 2025Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Modelscited by 9
  7. 2025A Multi-Granularity Retrieval Framework for Visually-Rich Documentscited by 6
  8. 2025High Fidelity Text to Image Generation with Contrastive Alignment and Structural Guidancecited by 6
  9. 2025Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approachcited by 5
  10. 2025Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysiscited by 5
  11. 2024Investigating Mixture of Experts in Dense Retrievalcited by 4
  12. 2025Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systemscited by 4
1 more
  1. 2023A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrievalcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Advancing Text Classification with Large Language Models and Neural Attention Mechanismscited by 1
  2. 2026Graph-Structured Deep Learning Framework for Multi-task Contention Identification with High-dimensional Metricscited by 1
  3. 2026CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimizationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
  2. 2025Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method
  3. 2024Retrieval-Augmented Generation with Estimation of Source Reliability
  4. 2025ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation
  5. 2026URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
  6. 2024Corrective Retrieval Augmented Generation
  7. 2024Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain
  8. 2024Better RAG using Relevant Information Gain