Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation

2026-01-14

AI Summary

This work addresses the limitations of existing retrieval-augmented generation (RAG) methods, which often lack structured organization when iteratively accumulating knowledge, thereby compromising the coherence and completeness of knowledge representation. To overcome this, the authors propose PAGER, a novel framework that introduces a page-driven, structured knowledge representation mechanism. PAGER guides large language models to construct multi-slot cognitive outlines, iteratively retrieves relevant information, and fills each knowledge slot accordingly, ultimately producing a structured context page to inform answer generation. By integrating prompt engineering, iterative retrieval, and slot-filling techniques, PAGER enables autonomous and orderly knowledge integration. Experimental results demonstrate that PAGER significantly outperforms current RAG approaches across multiple knowledge-intensive benchmarks and backbone models, yielding responses with higher information density, stronger consistency, reduced knowledge conflicts, and improved efficiency in leveraging external knowledge.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge. Recently, some works have incorporated iterative knowledge accumulation processes into RAG models to progressively accumulate and refine query-related knowledge, thereby constructing more comprehensive knowledge representations. However, these iterative processes often lack a coherent organizational structure, which limits the construction of more comprehensive and cohesive knowledge representations. To address this, we propose PAGER, a page-driven autonomous knowledge representation framework for RAG. PAGER first prompts an LLM to construct a structured cognitive outline for a given question, which consists of multiple slots representing a distinct knowledge aspect. Then, PAGER iteratively retrieves and refines relevant documents to populate each slot, ultimately constructing a coherent page that serves as contextual input for guiding answer generation. Experiments on multiple knowledge-intensive benchmarks and backbone models show that PAGER consistently outperforms all RAG baselines. Further analyses demonstrate that PAGER constructs higher-quality and information-dense knowledge representations, better mitigates knowledge conflicts, and enables LLMs to leverage external knowledge more effectively. All code is available at https://github.com/OpenBMB/PAGER.

Problem

• Retrieval-Augmented Generation
• structured knowledge representation
• knowledge organization
• iterative knowledge accumulation
• coherent knowledge representation

Innovation

• Retrieval-Augmented Generation
• Structured Knowledge Representation
• Contextual Pages
• Iterative Knowledge Refinement
• Cognitive Outline