# Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2511.13201 · HTML: https://mlsanity.com/paper/2511.13201/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [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)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://mlsanity.com/paper/2408.04948/) (2024)
- [StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization](https://mlsanity.com/paper/2410.08815/) (2024)
- [HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation](https://mlsanity.com/paper/2503.21322/) (2025)
- [PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths](https://mlsanity.com/paper/2502.14902/) (2025)
- [Retrieval-Augmented Generation with Hierarchical Knowledge](https://mlsanity.com/paper/2503.10150/) (2025)
- [Improving Retrieval Augmented Language Model with Self-Reasoning](https://mlsanity.com/paper/2407.19813/) (2024)
- [Self-supervised Hypergraph Representation Learning for Sociological Analysis](https://mlsanity.com/paper/2212.11440/) (2022)
- [Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning](https://mlsanity.com/paper/2311.03734/) (2023)
- [Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?](https://mlsanity.com/paper/2410.10083/) (2024)

## Built on by (most cited first, 9 of 9)

- [Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models](https://mlsanity.com/paper/2604.12185/) (2026)
- [G2-Reader: Dual Evolving Graphs for Multimodal Document QA](https://mlsanity.com/paper/2601.22055/) (2026)
- [FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A](https://mlsanity.com/paper/2606.07235/) (2026)
- [IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memory](https://mlsanity.com/paper/2602.07525/) (2026)
- [Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation](https://mlsanity.com/paper/2602.19543/) (2026)
- [MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers](https://mlsanity.com/paper/2604.04036/) (2026)
- [Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems](https://mlsanity.com/paper/2605.14259/) (2026)
- [Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement](https://mlsanity.com/paper/2608.16628/) (2026)
- [RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees](https://mlsanity.com/paper/2610.11370/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances the response quality and domain-specific performance of large language models (LLMs) by incorporating external knowledge to combat hallucinations. In recent research, graph structures have been integrated into RAG to enhance the capture of semantic relations between entities. However, it primarily focuses on low-order pairwise entity relations, limiting the high-order associations among multiple entities. Hypergraph-enhanced approaches address this limitation by modeling multi-entity interactions via hyperedges, but they are typically constrained to inter-chunk entity-level representations, overlooking the global thematic organization and alignment across chunks. Drawing inspiration from the top-down cognitive process of human reasoning, we propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations. Furthermore, we design a cognitive-inspired two-stage retrieval strategy that first activates query-relevant thematic content from the theme hypergraph, and then guides fine-grained recall and diffusion in the entity hypergraph, achieving semantic alignment and consistent generation from global themes to local details. Our extensive experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.