mlsanityData to 7 Oct 2026

SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data

arXiv 2602.16964 ↗First posted 18 Feb 2026cs.IRcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain, and inefficient to traverse at query time. In contrast, standard retriever-reader pipelines use flat similarity search over independently chunked text, missing multi-hop evidence chains across modalities. We propose SAGE (Structure Aware Graph Expansion) framework that (i) constructs a chunk-level graph offline using metadata-driven similarities with percentile-based pruning, and (ii) performs online retrieval by running an initial baseline retriever to obtain k seed chunks, expanding first-hop neighbors, and then filtering the neighbors using dense+sparse retrieval, selecting k' additional chunks. We instantiate the initial retriever using hybrid dense+sparse retrieval for implicit cross-modal corpora and SPARK (Structure Aware Planning Agent for Retrieval over Knowledge Graphs) an agentic retriever for explicit schema graphs. On OTT-QA and STaRK, SAGE improves retrieval recall by 5.7 and 8.5 points over baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 58 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

32 of 58 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths18 Feb
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)31 Dec
  3. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  4. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 27

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  6. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  7. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  8. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  9. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  10. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  11. 2020Open Question Answering over Tables and Textcited by 163
  12. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
15 more
  1. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 69
  2. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 59
  3. 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Basescited by 53
  4. 2022Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learningcited by 38
  5. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 24
  6. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  7. 2022Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQAcited by 17
  8. 2024Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrievalcited by 16
  9. 2024An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaborationcited by 16
  10. 2021Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selectioncited by 15
  11. 2022WarpGate: A Semantic Join Discovery System for Cloud Data Warehousescited by 13
  12. 2025Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Methodcited by 10
  13. 2025Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basescited by 9
  14. 2024Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answeringcited by 4
  15. 2025CRAFT: Training-Free Cascaded Retrieval for Tabular QAcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  2. 2026FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG
  3. 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
  4. 2026GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
  5. 2026Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation
  6. 2025The Structure-Content Trade-off in Knowledge Graph Retrieval
  7. 2026T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs
  8. 2026A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation