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

TL;DR

CHOP is a framework that improves retrieval accuracy in RAG systems by iteratively evaluating chunk relevance and preserving context, reducing confusion among similar documents.

Contribution

It introduces a novel chunkwise evaluation and reconstruction method using LLMs, enhancing document discrimination and retrieval precision.

Findings

Achieves a Top-1 Hit Rate of 90.77% on benchmark datasets.

Reduces semantic conflicts among similar documents.

Enhances ranking quality metrics in retrieval tasks.

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.