mlsanityData to 7 Oct 2026

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG

arXiv 2603.28773 ↗First posted 28 Jan 2026cs.IR cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon often known as hallucination). Retrieval augmented generation (RAG) tries to reduce factual errors by identifying information in a knowledge corpus and putting it in the context window of the model. While this approach is well-established for document-structured data, it is non-trivial to adapt it for Knowledge Graphs (KGs), especially for queries that require multi-node/multi-hop reasoning on graphs. We introduce UltRAG, a training-free KG-RAG recipe that combines LLM query generation, a fully inductive neural query executor, and LLM arbitration. This off-the-shelf composition achieves state-of-the-art results on Knowledge Graph Question Answering (KGQA) tasks without retraining the LLM or executor, while enabling language models to interface with Wikidata-scale graphs (116M entities, 1.6B relations) at comparable or lower costs. Our ablation studies indicate that these gains come from the full system design rather than from any single component.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

56 of 76 references.

References · 56

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2017Billion-scale similarity search with GPUscited by 2,477
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  7. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  9. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  12. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
38 more
  1. 2016Complex Embeddings for Simple Link Predictioncited by 897
  2. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  3. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  4. 2019Diffusion Improves Graph Learningcited by 414
  5. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  6. 2024Measuring short-form factuality in large language modelscited by 345
  7. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  8. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  9. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  10. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  11. 2024When Attention Sink Emerges in Language Models: An Empirical Viewcited by 200
  12. 2021Identity-aware Graph Neural Networkscited by 197
  13. 2019What Can Neural Networks Reason About?cited by 155
  14. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 148
  15. 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
  16. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 128
  17. 2019Neural Execution of Graph Algorithmscited by 118
  18. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  19. 2024Transformers need glasses! Information over-squashing in language taskscited by 87
  20. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  21. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  22. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  23. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  24. 2023A Comprehensive Survey on Automatic Knowledge Graph Constructioncited by 63
  25. 2022A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphscited by 49
  26. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 47
  27. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  28. 2020Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Studycited by 37
  29. 2024Simulation of Graph Algorithms with Looped Transformerscited by 29
  30. 2024The CLRS-Text Algorithmic Reasoning Language Benchmarkcited by 28
  31. 2025How Expressive are Knowledge Graph Foundation Models?cited by 22
  32. 2023Dual Algorithmic Reasoningcited by 21
  33. 2020XLVIN: eXecuted Latent Value Iteration Netscited by 17
  34. 2025The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factualitycited by 14
  35. 2022TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graphcited by 13
  36. 2024A Foundation Model for Zero-shot Logical Query Reasoningcited by 13
  37. 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarkingcited by 11
  38. 2025BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answeringcited by 10

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  2. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
  3. 2026RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
  4. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
  5. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  6. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
  7. 2025GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
  8. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation