ACL Findings2025
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M. Halappanavar, Jiliang Tang, Yu Wang
Abstract
Text-rich Graph Knowledge Bases (TG-KBs) have become increasingly crucial for answering queries by providing textual and structural knowledge. However, current retrieval methods often retrieve these two types of knowledge in isolation without considering their mutual reinforcement and some hybrid methods even bypass structural retrieval entirely after neighboring aggregation. To fill in this gap, we propose a Mixture of Structural-and-Textual Retrieval (MoR) to retrieve these two types of knowledge via a Planning-Reasoning-Organizing framework. In the Planning stage, MoR generates textual planning graphs delineating the logic for answering queries. Following planning graphs, in the Reasoning stage, MoR interweaves structural traversal and textual matching to obtain candidates from TG-KBs. In the Organizing stage, MoR further ranks fetched candidates by their structural trajectory. Extensive experiments demonstrate the superiority of MoR in harmonizing structural and textual retrieval with discovered insights, including uneven retrieving performance across different query logics and the benefits of integrating structural trajectories for candidate reranking. Our code is available at https://github.com/Yoega/MoR.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval cites G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval cites Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs cites G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs cites Knowledge Graph Prompting for Multi-Document Question Answering
- Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites GreaseLM: Graph REASoning Enhanced Language Models
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? cites G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Cited by top-tier papers4
- STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement LearningJuntong Ni, Shiyu Wang, Qi He, Ming Jin et al.ACL 2026 · 8 citations
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?Junchi Yu, Yujie Liu, Jindong Gu, Philip H. S. Torr et al.NeurIPS 2025 · 8 citations
- Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth RetrievalJoaquín Polonuer, Lucas Vittor, Iñaki Arango, Ayush Noori et al.ACL 2026 · 1 citation
- Reasoning by Exploration: A Unified Approach to Retrieval and Generation over GraphsHaoyu Han, Kai Guo, Harry Shomer, Yu Wang et al.WWW 2026 · 1 citation
Builds on16
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui PanICLR 2024 · 499 citations
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringXiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla et al.NeurIPS 2024 · 384 citations
- Knowledge Graph Prompting for Multi-Document Question AnsweringYu Wang, Nedim Lipka, Ryan A. Rossi, Alexa F. Siu et al.AAAI 2024 · 290 citations
- GreaseLM: Graph REASoning Enhanced Language ModelsXikun Zhang, Antoine Bosselut, Michihiro Yasunaga, Hongyu Ren et al.ICLR 2022 · 285 citations
Related papers
- CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever ArchitectureZaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu et al.EMNLP Findings 2025 · 1 citation
- HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge BasesMeng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han et al.ACL 2025
- A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge GraphsYimin Deng, Yuxia Wu, Yejing Wang, Guoshuai Zhao et al.ACL Findings 2025 · 3 citations
- PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented GenerationXiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu et al.WWW 2026 · 1 citation
- Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge GraphsYanlin Song, Ben Liu, Víctor Gutiérrez-Basulto, Zhiwei Hu et al.WWW 2026
