Latest Knowledge Graphs Research Papers

The newest Knowledge Graphs papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Knowledge Graphs so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
  ACL ARR 2026 May Submission · May 25, 2026

  Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Graph RAG integrates knowledge graphs into the retrieval pipeline, enabling LLMs to access ent…

• Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG
  Riccardo Terrenzi, Maximilian von Zastrow, Serkan Ayvaz · arXiv · May 14, 2026

  Retrieval-Augmented Generation can improve factuality by grounding answers in external evidence, but Agentic GraphRAG complicates what it means for citations to be faithful. In these systems, an agent explores a knowledge graph before produ…

• SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering
  Jiujiu Chen, Yazheng Liu, Sihong Xie, Hui Xiong · arXiv · May 4, 2026

  Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise supervision, they often suffer from a risk compensation effect, where incorrect …

• Fine-Grained Graph Generation through Latent Mixture Scheduling
  Nidhi Vakil, Hadi Amiri · arXiv · May 4, 2026

  Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling, and knowledge graph construction. Unlike existing methods th…

• Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
  Gongbo Zhang, Wen Wang, Ye Tian, Li Yuan · arXiv · Apr 29, 2026

  Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference…

• XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation
  Zhuoling Li, Ha Linh Hong Tran Nguyen, Valeria Bladinieres, Maxim Romanovsky · arXiv · Apr 27, 2026

  Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a structured, semantically coherent context, yielding more grounded answers. However, GraphRA…

• Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems
  Pavel Salovskii, Iuliia Gorshkova · arXiv · Apr 22, 2026

  This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer. Instead of relying solely on parametric knowledge and vector-based retrieval (RA…

• VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
  Jean Mercat, Sedrick Keh, Kushal Arora, Isabella Huang et al. · arXiv · Apr 21, 2026

  We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the action training stage, often stitching together incompatible pretraining pipelines…

• Using Large Language Models and Knowledge Graphs to Improve the Interpretability of Machine Learning Models in Manufacturing
  Thomas Bayer, Alexander Lohr, Sarah Weiß, Bernd Michelberger et al. · arXiv · Apr 17, 2026

  Explaining Machine Learning (ML) results in a transparent and user-friendly manner remains a challenging task of Explainable Artificial Intelligence (XAI). In this paper, we present a method to enhance the interpretability of ML models by u…

• Entity Integrity: Maintaining Accurate Representation in AI Knowledge Graphs
  Rex Fraction, Lee Sharks · Zenodo (CERN European Organ... · Apr 14, 2026

  EA-EI-01 — Practice definition for Entity Integrity: ensuring AI systems represent an entity as a distinct, correctly attributed node. Catalogs five failure modes: Entity Collision, Entity Fragmentation, Attribution Drift, Category Absorpti…

• LEE SHARKS — Knowledge Graph and Metadata Packet for AI Indexing: Canonical Identity, Disambiguation, and Complete Archive Map (Crimson Hexagonal Archive)
  Lee Sharks · Zenodo (CERN European Organ... · Apr 12, 2026

  Canonical knowledge graph and metadata packet for AI indexing of Lee Sharks (ORCID: 0009-0000-1599-0703) and the Crimson Hexagonal Archive. DISAMBIGUATION: Lee Sharks is NOT Lee Sharkey (Anthropic, mechanistic interpretability). Sharks stud…

• LEE SHARKS — Knowledge Graph and Metadata Packet for AI Indexing: Canonical Author Identity, Disambiguation Protocol, and Entity Map (EA-KG-01) — Crimson Hexagonal Archive
  Lee Sharks · Zenodo (CERN European Organ... · Apr 12, 2026

  LEE SHARKS — Knowledge Graph and Metadata Packet for AI Indexing. Canonical author identity, disambiguation protocol, and entity map for the Crimson Hexagonal Archive. CRITICAL DISAMBIGUATION: Lee Sharks IS NOT Lee Sharkey (mechanistic inte…

• VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph Dataset for Retrieval-Augmented Generation
  Hyeongcheol Park, Jiyoung Seo, MinHyuk Jang, Hogun Park et al. · ICLR 2026 Conference Withdrawn Submission · Sep 19, 2025

  Multimodal Knowledge Graphs (MMKGs), which represent explicit knowledge across multiple modalities, play a pivotal role by complementing the implicit knowledge of Multimodal Large Language Models (MLLMs) and enabling more grounded reasoning…

• Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
  Xusheng Cao, Haori Lu, Linlan Huang, Fei Yang et al. · NeurIPS 2025 poster · Sep 18, 2025

  Continual learning in computer vision faces the critical challenge of catastrophic forgetting, where models struggle to retain prior knowledge while adapting to new tasks. Although recent studies have attempted to leverage the generalizatio…

• SKILL: Structural Knowledge Injection into Large Language Models for Inductive Knowledge Graph Reasoning
  Lei Gao, Ben Zhang, Jinchuan Zhang, Ling Tian et al. · Submitted to ICLR 2026 · Sep 17, 2025

  Knowledge Graph Reasoning (KGR) aims to predict missing (head, relation, tail) triples by inferring new facts from existing ones within a knowledge graph. While recent methods embed entities and relations into vectors or model multi-hop pat…

• SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration
  Keyan Ding, Jing Yu, Junjie Huang, Yuchen Yang et al. · Nature Computational Science · Jul 27, 2025

  Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools requires substantial domain expertise. While large language models show promise in tool automation, they struggle to seamlessl…

• LLM-DDI: Leveraging Large Language Models for Drug-Drug Interaction Prediction on Biomedical Knowledge Graph
  Dongxu Li, Yue Yang, Ziwen Cui, Hengchuang Yin et al. · IEEE journal of biomedical and health informatics · Jul 2, 2025

  Drug-drug interaction (DDI) refers to the interaction relationships between drugs. Discovering new DDIs is crucial for advancing drug development and enhancing clinical treatments. Given the significant progress achieved through graph neura…

• AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
  Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong et al. · arXiv.org · May 29, 2025

  We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously extract knowledge triples and induce compre…

• Large language model assisted fine-grained knowledge graph construction for robotic fault diagnosis
  Xingming Liao, Chong Chen, Zhuowei Wang, Ying Liu et al. · Advanced Engineering Informatics · May 1, 2025

  With the rapid deployment of industrial robots in manufacturing, the demand for advanced maintenance techniques to sustain operational efficiency has become crucial. Fault diagnosis Knowledge Graph (KG) is essential as it interlinks multi-s…

• CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
  Hanxiang Xu, Wei Ma, Ti Zhou, Yanjie Zhao et al. · 2025 IEEE/ACM 47th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · Apr 27, 2025

  In recent years, the programming capabilities of large language models (LLMs) have garnered significant attention. Fuzz testing, a highly effective technique, plays a key role in enhancing software reliability and detecting vulnerabilities.…

• Knowledge Graph Construction: Extraction, Learning, and Evaluation
  Seungmin Choi, Yuchul Jung · Applied Sciences · Mar 28, 2025

  A Knowledge Graph (KG), which structurally represents entities (nodes) and relationships (edges), offers a powerful and flexible approach to knowledge representation in the field of Artificial Intelligence (AI). KGs have been increasingly a…

• Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning
  Junming Liu, Siyuan Meng, Yanting Gao, Song Mao et al. · IEEE International Conference on Computer Vision · Mar 17, 2025

  Multimodal reasoning in Large Language Models (LLMs) struggles with incomplete knowledge and hallucination artifacts, challenges that textual Knowledge Graphs (KGs) only partially mitigate due to their modality isolation. While Multimodal K…

• Using knowledge graph in adapting language model on mathematical text
  Ольга Атаева, Natalia Tuchkova · MathAI 2025 Oral · Mar 9, 2025

  The subject of the study is the problem of adapting language models to scientific subject areas. The issues of expanding language models to mathematical subject areas are considered. It is proposed to use the knowledge graph of the subject …

• Utilizing Language Models For Synthetic Knowledge Graph Generation
  Shuran Fu, Peihua Mai, Zhang Jingqi, Yan Pang · ICLR 2025 Workshop Data Problems Poster · Mar 6, 2025

  Knowledge Graphs play a pivotal role in various machine-learning tasks. However, constructing these datasets is challenging due to their semantic and structural complexity, often resulting in limited data size. Synthetic graph generation ha…

• Construction of a knowledge graph for framework material enabled by large language models and its application
  Xuefeng Bai, Song He, Yi Li, Yabo Xie et al. · npj Computational Materials · Feb 27, 2025
• How Expressive are Knowledge Graph Foundation Models?
  Xingyue Huang, Pablo Barceló, Michael M. Bronstein, I. Ceylan et al. · International Conference on Machine Learning · Feb 18, 2025

  Knowledge Graph Foundation Models (KGFMs) are at the frontier for deep learning on knowledge graphs (KGs), as they can generalize to completely novel knowledge graphs with different relational vocabularies. Despite their empirical success, …

• Knowledge Graph-Guided Retrieval Augmented Generation
  Xiangrong Zhu, Yuexiang Xie, Yi Liu, Yaliang Li et al. · North American Chapter of the Association for Computational Linguistics · Feb 8, 2025

  Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based ap…

• MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot
  Xuejiao Zhao, Siyan Liu, Su-Yin Yang, C. Miao · The Web Conference · Feb 6, 2025

  Retrieval-augmented generation (RAG) is a well-suited technique for retrieving privacy-sensitive Electronic Health Records (EHR). It can serve as a key module of the healthcare copilot, helping reduce misdiagnosis for healthcare practitione…

• Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models
  Hanzhu Chen, Xu Shen, Jie Wang, Zehao Wang et al. · ICLR 2025 Poster · Jan 22, 2025

  Despite the impressive performance of general large language models(LLMs), many of their applications in specific domains (e.g., low-data and knowledge-intensive) still confront significant challenges. Supervised fine-tuning (SFT)---where a…

• LLM-Assisted Knowledge Graph Completion for Curriculum and Domain Modelling in Personalized Higher Education Recommendations
  Hasan Abu-Rasheed, Constance Jumbo, Rashed Al Amin, Christian Weber et al. · IEEE Global Engineering Education Conference · Jan 21, 2025

  While learning personalization offers great potential for learners, modern practices in higher education require a deeper consideration of domain models and learning contexts, to develop effective personalization algorithms. This paper intr…