paper-with-me

홈 › Papers

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

2025-10-30 · Xiaofan Guo, Yaxuan Luan, Yue Kang, Xiangchen Song, Jinxu Guo 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.

📄 PDF Abstract BibTeX arXiv:2510.27054

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Query-Centric Graph Retrieval Augmented Generation

2025-09-25 · Yaxiong Wu, Jianyuan Bo, Yongyue Zhang, Sheng Liang 외 arxiv

Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine…

Long-Context UnderstandingQuestion Answering

EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory

2026-08-12 · Le Zhang, Hao Chen, Vlad Roznyatovskiy, Jianzhong Zhang 외 arxiv

Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in existing systems: indices built from context-poor captions…

KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG

2025-02-13 · Yiqian Huang, Shiqi Zhang, Xiaokui Xiao

Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful in domains such as biomedicine, law, and political science, w…

Knowledge GraphsLarge Language ModelQuestion AnsweringRAG+2

Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG

2026-08-24 · Zhe Jin, Zhimin Lin, Bin Zheng, Junhua Fang 외 arxiv

Graph-based retrieval-augmented generation (RAG) provides a scalable paradigm for long-video understanding, but existing systems typically inherit a fixed temporal granularity from video segmentation when constructing th…

Video SegmentationAnswer Generation

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

2026-09-15 · Aurélien Pellet, Julien Perez, Marie Puren arxiv

Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where…