DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding

• URL: http://arxiv.org/abs/2607.24554v1
• Date: Mon, 27 Jul 2026 15:28:02 GMT
• Title: DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding
• Abstract summary: We introduce DeCoRAG, a multimodal Graph RAG pipeline that shifts knowledge processing from coupled visual-semantic reasoning to "Cognitive Decoupling"<n>DeCoRAG improves the semantic pass rate by up to 12.5 percentage points over the strongest baseline.<n>RAP-Crop reduces offline graph-construction prompt tokens by 40.8% without sacrificing end-to-end accuracy.
• Score: 9.340832029984703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advancing multimodal retrieval-augmented generation (RAG) for complex document understanding presents a formidable dual dilemma of accuracy and efficiency, particularly in graph RAG. Processing structurally sparse yet visually dense layouts, such as extracting a tiny data marker from a financial chart, often incurs computationally prohibitive token overhead while still triggering catastrophic hallucination. However, multimodal Graph RAG pipelines rely on graph-construction stages that assume Vision-Language Models (VLMs) can resolve sparse semantics within high-density layouts. We challenge this assumption, revealing that forcing VLMs to localize visual evidence, interpret semantics, and extract relations triggers a "Visual Attention Sink," a mechanism driving catastrophic semantic loss, while full-page processing incurs massive computational overhead. Controlled interventions verify that this failure is boundary-driven rather than content-specific and that semantic anchoring mitigates it. To fundamentally correct this flawed paradigm, we introduce DeCoRAG, a multimodal Graph RAG pipeline that shifts knowledge processing from coupled visual-semantic reasoning to "Cognitive Decoupling." Rather than passively processing raw pixels, its graph-construction stage establishes a macroscopic Semantic Anchor to neutralize the attention sink. This anchor subsequently drives our Region-Aware Pruning and Cropping (RAP-Crop) mechanism, shifting the reasoning space from dense, noisy backgrounds to purified, intent-driven semantic clusters. The resulting graph supports hybrid retrieval and answer generation. Across complex document benchmarks, DeCoRAG improves the semantic pass rate by up to 12.5 percentage points over the strongest baseline and generalizes to DocVQA. RAP-Crop reduces offline graph-construction prompt tokens by 40.8% without sacrificing end-to-end accuracy.

Related papers

• LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals [50.157719466558696]
  We show that modern generators exhibit low-rank collapse in the semantic-residual subspace while preserving the dominant semantic direction.<n>We propose textbfLoRC, a framework that decouples semantic dominance to capture the collapsed residual geometry.<n>Our method improves accuracy by an average of 7.0% across multiple benchmarks and achieves 97.0% accuracy on 39 unseen generators.
  arXiv  Detail & Related papers  (2026-08-21T08:58:47Z)
• RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT [0.014257559724536567]
  Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.<n>We propose a depth-aware token reduction framework that adapts reduction strategies to the layer-wise characteristics of token representations.<n>Our framework provides a training-free template for optimizing vision models by aligning reduction strategies with hierarchical feature evolution.
  arXiv  Detail & Related papers  (2026-06-06T13:13:02Z)
• Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion [71.20734649881258]
  Real-world multimodal datasets often suffer from modality incompleteness due to sensor failures, annotation scarcity, or privacy constraints.<n>One effective solution is modality completion, which reconstructs missing features to provide modality-complete graphs for downstream tasks.<n>We propose GRE-MC, a Graph Retrieval-Enhanced Modality Completion framework, to overcome these limitations.
  arXiv  Detail & Related papers  (2026-05-01T13:50:52Z)
• Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees [10.806910118253976]
  Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships.<n>We propose Query-Aware Flow Diffusion RAG (QAFD-RAG), a training-free framework that dynamically adapts graph traversal to each query's holistic semantics.<n>QAFD-RAG recovers relevant subgraphs with high probability under mild signal-to-noise conditions.
  arXiv  Detail & Related papers  (2026-04-21T08:53:34Z)
• Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs [39.73839943827917]
  INSES is a dynamic framework designed to reason beyond explicit edges.<n>It couples LLM-guided navigation, which prunes noise and steers exploration, with embedding-based similarity expansion.<n>It consistently outperforms SOTA RAG and GraphRAG baselines across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-03-14T16:16:47Z)
• HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG [53.30561659838455]
  Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations.<n>Retrieval-Augmented Generation (RAG) frequently overlooks structural interdependencies essential for multi-hop reasoning.<n>Help achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$times$ speedup over leading Graph-based RAG baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:05:29Z)
• ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization [62.03035862528452]
  ForgeryVCR is a framework that materializes imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning.<n>ForgeryVCR achieves state-of-the-art (SOTA) performance in both detection and localization tasks.
  arXiv  Detail & Related papers  (2026-02-15T11:14:47Z)
• Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning [32.78218766121055]
  Graph retrieval-augmented generation (GraphRAG) has effectively enhanced large language models in complex reasoning.<n>We propose a vertically unified agentic paradigm, Youtu-GraphRAG, to jointly connect the entire framework as an intricate integration.
  arXiv  Detail & Related papers  (2025-08-27T13:13:20Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [79.75818239774952]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.