CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2609.04647v1
• Date: Fri, 04 Sep 2026 02:27:34 GMT
• Title: CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation
• Abstract summary: Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query.<n>We introduce Coherence-Aware Graph AGE (CAGE), a reranking framework that models "between-chunk coherence"<n>Our pipeline transforms retrieved passages into directed heterogeneous entity graphs.
• Score: 2.3578002163476266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectively incoherent. We introduce Coherence-Aware Graph Encoding (CAGE), a reranking framework that models "between-chunk coherence" across four dimensions: Intra-Domain Relevance, Noise Resistance, Informational Bonding, and Factual Consistency. Our pipeline transforms retrieved passages into directed heterogeneous entity graphs, amplifies factual anchors via min-out-degree reweighting, encodes structural patterns through a Relational Graph Convolutional Network, and fuses inter-chunk coherence with query relevance for final ranking. Evaluated across four multi-hop benchmarks, CAGE matches or outperforms strong baselines including monoT5 in Recall@5 on bridge-dominated datasets and consistently improves downstream Exact Match, demonstrating that structurally coherent context yields more precise answers even when retrieval recall is comparable or lower.

Related papers

• GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG [0.5566372336864309]
  We introduce GRADRAG, a framework for cross-component prompt adaptation.<n>An Evaluator critiques downstream answers and supporting evidence, producing actionable feedback.<n>We evaluate GRADRAG on the SQUALITY and QMSUM benchmarks.
  arXiv  Detail & Related papers  (2026-07-23T13:54:38Z)
• HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution [4.180315687162217]
  HAGE is a weighted multi-relational memory framework for agentic large language model (LLM) systems.<n>Given a query, an LLM-based classifier identifies the relational intent, and a routing network dynamically modulates the corresponding dimensions of the edge embedding.<n>Traversal scores are computed via a learned combination of semantic similarity and these query-conditioned edge representations.
  arXiv  Detail & Related papers  (2026-05-11T03:41:18Z)
• 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 Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants [3.037387520023979]
  We introduce RelSC, a new graph-regression dataset built from program graphs.<n>Each graph is labelled with the execution-time cost of the corresponding program.<n>We evaluate a diverse set of graph neural network architectures on both variants of RelSC.
  arXiv  Detail & Related papers  (2025-05-29T12:59:36Z)
• CORG: Generating Answers from Complex, Interrelated Contexts [57.213304718157985]
  In a real-world corpus, knowledge frequently recurs across documents but often contains inconsistencies due to ambiguous naming, outdated information, or errors.<n>Previous research has shown that language models struggle with these complexities, typically focusing on single factors in isolation.<n>We introduce Context Organizer (CORG), a framework that organizes multiple contexts into independently processed groups.
  arXiv  Detail & Related papers  (2025-04-25T02:40:48Z)
• Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence [51.54175067684008]
  This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. We first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes. Our framework is evaluated on standard benchmarks for semantic matching, and also applied to geometric matching, where we show that our approach achieves significant improvements compared to existing methods.
  arXiv  Detail & Related papers  (2024-03-17T07:02:55Z)
• Learnable Pillar-based Re-ranking for Image-Text Retrieval [119.9979224297237]
  Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. We propose a novel learnable pillar-based re-ranking paradigm for image-text retrieval.
  arXiv  Detail & Related papers  (2023-04-25T04:33:27Z)
• Plug-and-Play Regulators for Image-Text Matching [76.28522712930668]
  Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching. We develop two simple but quite effective regulators which efficiently encode the message output to automatically contextualize and aggregate cross-modal representations. Experiments on MSCOCO and Flickr30K datasets validate that they can bring an impressive and consistent R@1 gain on multiple models.
  arXiv  Detail & Related papers  (2023-03-23T15:42:05Z)
• Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences [53.09276639185084]
  Multi-view anchor graph clustering selects representative anchors to avoid full pair-wise similarities. Existing approaches do not pay sufficient attention to establishing correct correspondences between the anchor sets across views.
  arXiv  Detail & Related papers  (2022-05-30T13:07:40Z)

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.