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

arXiv: https://arxiv.org/abs/2510.27054 · HTML: https://mlsanity.com/paper/2510.27054/

## 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.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 15 of 15)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.14891/) (2025)
- [UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.02719/) (2024)
- [Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis](https://mlsanity.com/paper/2505.07459/) (2025)
- [CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity](https://mlsanity.com/paper/2410.12248/) (2024)
- [Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models](https://mlsanity.com/paper/2510.01231/) (2025)
- [Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.05312/) (2025)
- [Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Models](https://mlsanity.com/paper/2509.03057/) (2025)
- [A Multi-Granularity Retrieval Framework for Visually-Rich Documents](https://mlsanity.com/paper/2505.01457/) (2025)
- [High Fidelity Text to Image Generation with Contrastive Alignment and Structural Guidance](https://mlsanity.com/paper/2508.10280/) (2025)
- [Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach](https://mlsanity.com/paper/2508.06155/) (2025)
- [Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysis](https://mlsanity.com/paper/2508.14509/) (2025)
- [Investigating Mixture of Experts in Dense Retrieval](https://mlsanity.com/paper/2412.11864/) (2024)
- [Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systems](https://mlsanity.com/paper/2509.04694/) (2025)
- [A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval](https://mlsanity.com/paper/2312.02538/) (2023)

## Built on by (most cited first, 3 of 3)

- [Advancing Text Classification with Large Language Models and Neural Attention Mechanisms](https://mlsanity.com/paper/2512.09444/) (2025)
- [Graph-Structured Deep Learning Framework for Multi-task Contention Identification with High-dimensional Metrics](https://mlsanity.com/paper/2601.20389/) (2026)
- [CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization](https://mlsanity.com/paper/2602.18786/) (2026)

## 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.