CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents

2026-04-17

AI Summary

This work addresses the challenges of retrieval confusion, information redundancy, and factual inaccuracies in existing Retrieval-Augmented Generation (RAG) systems when handling semantically similar documents in multi-document settings. To mitigate these issues, the authors propose a context-aware retrieval enhancement approach that generates compact textual chunk signatures via a CNM-Extractor and incorporates a continuity decision module. This module leverages large language models to assess thematic coherence and structural continuity between chunks, thereby enriching each chunk with context-aware metadata. The proposed method effectively alleviates semantic conflicts among similar documents, achieving a Top-1 hit rate of 90.77% on standard benchmarks and significantly improving retrieval ranking quality, thus offering a novel paradigm for constructing high-fidelity knowledge bases.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Information Extraction
• Knowledge Representation and Reasoning: Other Foundations of Knowledge Representation & Reasoning

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) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and factual errors. To alleviate this issue, we propose CHOP, a framework that iteratively evaluates chunk relevance with Large Language Models (LLMs) and progressively reconstructs documents by determining their association with specific topics or query types. CHOP integrates two key components: the CNM-Extractor, which generates compact per-chunk signatures capturing categories, key nouns, and model names, and the Continuity Decision Module, which preserves contextual coherence by deciding whether consecutive chunks belong to the same document flow. By prefixing each chunk with context-aware metadata, CHOP reduces semantic conflicts among similar documents and enhances retriever discrimination. Experiments on benchmark datasets show that CHOP alleviates retrieval confusion and provides a scalable approach for building high-quality knowledge bases, achieving a Top-1 Hit Rate of 90.77% and notable gains in ranking quality metrics.

Problem

• Retrieval-Augmented Generation
• multi-document retrieval
• retrieval accuracy
• semantic conflicts
• factual errors

Innovation

• Chunkwise Context-Preserving
• Retrieval-Augmented Generation
• CNM-Extractor
• Continuity Decision Module
• Context-Aware Metadata