---
title: "Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG"
authors:
  - "Jiarui Zhong"
  - "Hong Cai Chen"
doi: "10.24963/ijcai.2026/679"
url: "https://ijcai.org/proceedings/2026/679"
pdf: "https://ijcai.org/proceedings/2026/0679.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6101-6108"
track: "Main Track"
keywords:
  - "Natural Language Processing: Question answering"
  - "Natural Language Processing: Information extraction"
  - "Data Mining: Knowledge graphs and knowledge base completion"
  - "Natural Language Processing: Information retrieval and text mining"
---

# Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG

Jiarui Zhong, Hong Cai Chen

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6101-6108. DOI: [10.24963/ijcai.2026/679](https://doi.org/10.24963/ijcai.2026/679)

## Abstract

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pseudo-evidence, while graph-based RAG is frequently hindered by search-time pruning, which may discard potentially valid reasoning paths. Existing hybrid approaches primarily adopt simple evidence concatenation or unidirectional enhancement, which fails to address the fundamental "Information Island" problem caused by asymmetric reasoning flows between unstructured text and structured graphs. We propose TGS-RAG, a unified framework for Text-Graph Synergistic enhancement. TGS-RAG introduces a bidirectional mechanism: (i) a Graph-to-Text channel that employs a Global Voting strategy from visited graph nodes to re-rank and refine textual evidence, filtering out semantic noise; and (ii) a Text-to-Graph channel that utilizes the Memory-based Orphan Entity Bridging algorithm. This algorithm utilizes textual cues to proactively resurrect valid but previously pruned reasoning paths from the search history without additional database overhead. Experimental results on multiple multi-hop reasoning benchmarks demonstrate that TGS-RAG significantly outperforms state-of-the-art baselines, achieving a superior balance between retrieval precision and computational efficiency.