# HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases

arXiv: https://arxiv.org/abs/2412.16311 · HTML: https://mlsanity.com/paper/2412.16311/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://mlsanity.com/paper/2405.20139/) (2024)
- [Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs](https://mlsanity.com/paper/2404.07103/) (2024)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2404.13207/) (2024)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [Don't Forget to Connect! Improving RAG with Graph-based Reranking](https://mlsanity.com/paper/2405.18414/) (2024)

## Built on by (most cited first, 29 of 29)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2507.21892/) (2025)
- [Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases](https://mlsanity.com/paper/2502.20317/) (2025)
- [BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering](https://mlsanity.com/paper/2507.04127/) (2025)
- [Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?](https://mlsanity.com/paper/2510.16582/) (2025)
- [GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases](https://mlsanity.com/paper/2504.05478/) (2025)
- [GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases](https://mlsanity.com/paper/2605.30237/) (2026)
- [RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning](https://mlsanity.com/paper/2512.09487/) (2025)
- [Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion](https://mlsanity.com/paper/2606.14885/) (2026)
- [Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge](https://mlsanity.com/paper/2505.09246/) (2025)
- [GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.22009/) (2025)
- [Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval](https://mlsanity.com/paper/2601.13969/) (2026)
- [See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Models](https://mlsanity.com/paper/2510.16769/) (2025)
- [CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale](https://mlsanity.com/paper/2601.06564/) (2026)
- [Disco-RAG: Discourse-Aware Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.04377/) (2026)
- [Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data](https://mlsanity.com/paper/2601.04764/) (2026)
- [Beyond Pipelines: A Fundamental Study on the Rise of Generative-Retrieval Architectures in Web Research](https://mlsanity.com/paper/2602.17450/) (2026)
- [Training-Free Test-Time Contrastive Learning for Large Language Models](https://mlsanity.com/paper/2604.13552/) (2026)
- [RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.17072/) (2026)
- [GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG](https://mlsanity.com/paper/2607.21324/) (2026)
- [LivingRAG: Augmenting Graph RAG with Experience](https://mlsanity.com/paper/2608.25960/) (2026)
- [R2Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG](https://mlsanity.com/paper/2609.02894/) (2026)
- [Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction](https://mlsanity.com/paper/2609.06391/) (2026)
- [Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy](https://mlsanity.com/paper/2609.12791/) (2026)
- [FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Exploration](https://mlsanity.com/paper/2609.19601/) (2026)
- [Beyond Similarity through Zero-Token Geometric Graphs for Multi-Hop RAG](https://mlsanity.com/paper/2609.19622/) (2026)
- [Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning](https://mlsanity.com/paper/2610.08894/) (2026)
- [Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval](https://mlsanity.com/paper/2610.14465/) (2026)
- [Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve](https://mlsanity.com/paper/2610.18616/) (2026)

## Abstract (arXiv)

Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions? Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source. However, many questions require both textual and relational information from SKB - referred to as "hybrid" questions - which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information. In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA consisting of a retriever bank and a critic module, with the following advantages: (1) Agentic, it automatically refines the output by incorporating feedback from the critic module, (2) Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank, (3) Interpretable, it justifies decision making with intuitive refinement path, and (4) Effective, it surpasses all baselines on HQA benchmarks. In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51%.