Knowledge Graph Question Answering

Also known as KGQA

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 140% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 91

All topics

Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation
Jul 20, 2026Blake G. Fitch, Cato Elia KurtzKnowledge Representation Knowledge Graph Question Answering
Max Planck Institute for Biological Cybernetics Tübingen, Germany
CODENS: Transforming Code Changes into Living, Accessible, and Queryable Documentation
Jul 20, 2026Abdelhak Kelious, Chyrine Tahri, Eliot BardetKG Construction Graph Retrieval-Augmented Generation
CAPSENS Paris, France
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph
Jul 19, 2026Peiji Yu, Xin Chen, Tianxing WuKnowledge Augmentation for Language Models Multi-Agent Debate
School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China
SmartRAG: Native Graph-Based RAG for Mobile Device
Jul 16, 2026Zhihan Jiang, Meng Li, Shenghao Liu +5Named Entity Recognition On-Device Language Model Inference
1Nanjing University · 2HUST · 3Southeast University
MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
Jul 16, 2026Nikit Srivastava, Daniel Vollmers, René Speck +3Multi-Hop QA LLM Grounding
Data Science Group, Heinz Nixdorf Institute, Paderborn University, Germany
SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation
Jul 16, 2026Yiming Zhang, Koji TsudaLLM Grounding Knowledge Graph Question Answering
1The University of Tokyo, Japan · Center for Basic Research on Materials, National Institute for Materials Science, Japan · 3RIKEN Center for Advanced Intelligence Project, Japan
InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs
Jul 8, 2026Mayank Kharbanda, Michael Cochez, Rajiv Ratn Shah +1KG Embedding Knowledge Graph Question Answering
IIIT-Delhi, India · Vrije Universiteit, Amsterdam, The Netherlands · Ellis Institute Finland +2
RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
Jul 7, 2026Sambaran Bandyopadhyay, Ananth MuppidiMulti-Hop QA LLM Reasoning with Graphs
Adobe Research · Adobe Systems
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
Jun 30, 2026Bao Long Nguyen Huu, Atsushi HashimotoGraph Representation Learning Graph SSL
OMRON Corporation · OMRON SINIC X Corporation
Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs
Jun 28, 2026Vignesh Ram Nithin Kappagantula, Shayan Hassantabar, Samuel Simpson +1LLM Grounding LLM Reasoning with Graphs
Expedia Group Seattle, Washington, USA
Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering
Jun 26, 2026Yongxue Shan, Meihan Wu, Cundi Fang +2Multi-Hop QA Graph-Based Retrieval
National University of Defense Technology · Changsha, China · Pengcheng Laboratory +1
KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems
Jun 26, 2026Minjun Choi, Yerin Kim, Junghyuk Seo +3Text-to-Cypher Knowledge Graph Question Answering
Sungkyunkwan University · NAVER
Fuzzy Quantification over OWL Ontologies and Knowledge Graphs
Jun 24, 2026Enrique Palacín, Fernando Bobillo, Ignacio Huitzil +2Fuzzy Logic Knowledge Graph Question Answering
University of Zaragoza, Zaragoza, Spain · Aragon Institute of Engineering Research (I3A), Zaragoza, Spain · University of Bari Aldo Moro, Bari, Italy +1
TTFT-Aware Graph Chain-of-Thought:Distance-Indexed Neural A* for Low-Hallucination Multi-Hop Medical Reasoning
Jun 22, 2026Bechir Dardouri, Kaïs Zhioua, Yassine MsaddakInference-Time Search LLM Hallucination Mitigation
Tanit Healthcare Technologies, Tunisia
Weaving Multi-Source Evidence for Biomedical Reasoning: The BioMedHop Benchmark and BioWeave Framework
Jun 15, 2026Xingyu Tan, Shiyuan Liu, Xiaoyang Wang +5Multi-Hop QA Evidence-Grounded Reasoning
University of New South Wales, Australia · 2CSIRO, Australia · University of Technology Sydney, Australia
DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts
Jun 14, 2026Zijian Carl Ma, Sean J. Wang, Sijbren Kramer +1Historical Document Analysis Multi-Agent LLM Systems
Department of Bioengineering · Stanford University · Amazon AWS AI
When Correct Edges Cannot Be Verified: A Provenance Gap in Incomplete KGQA and a Provenance-Favoring Completion Policy
Jun 14, 2026Yongqi Kang, Yu Fu, Yong ZhaoData Provenance Selective Prediction
Sichuan University
Semantic Reasoning in Medicine: The Role of Knowledge Graphs Across Five Key Domains
Jun 13, 2026Haniye Sherafatmandjoo, Mohammad Akbari, Zahed RahmatiKG Construction Healthcare
Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran
Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs
Jun 4, 2026Grama ChethanLLM Reasoning with Graphs LLM Planning
Siemens Digital Industries Software
Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval
Jun 3, 2026Padmaja Jonnalagedda, Yuguang Yao, Xiang Gao +2KG Construction Knowledge Representation
Intuit AI Research
CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment
Jun 3, 2026Nikodem TomczakText-to-Cypher Knowledge Graph Question Answering
Thulge Labs, Singapore
Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation
Jun 3, 2026Xin Zhang, Yang Cao, Baoxing Wu +2LLM Grounding LLM Reasoning with Graphs
School of Information Science and Engineering, Chongqing Jiaotong University · School of Computer Science and Technology, Chongqing University of Posts and Telecommunications
Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs
Jun 2, 2026Weiwei Ding, Zixuan Li, Long Bai +7LLM Grounding LLM Reasoning with Graphs
1Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · 2Shandong University · 3Shandong University-Weihai Research Institute of Industrial Technology
3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledge Graph Retrieval
Jun 1, 2026Raghad Albusayes, Munirah AlyahyaVideo QA Egocentric Video Understanding
TAHAKOM
KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
May 29, 2026Albert Sawczyn, Piotr Bielak, Tomasz KajdanowiczLLM Hallucination Detection Knowledge Graph Question Answering
Department of Artificial Intelligence Wrocław University of Science and Technology Wrocław, Poland
DeSQ: Decomposition-based SPARQL Query Generation
May 29, 2026Papa Abdou Karim Karou Diallo, Aditya Sharma, Neshat Elhami Fard +1Question Decomposition Entity Linking
LAMA-WeST · Mila – Quebec AI Institute · Polytechnique Montréal
mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol
May 28, 2026Peter W. Rose, Benjamin M. Good, Amanda M. Saravia-Butler +7Knowledge Graph Question Answering Knowledge Graphs
San Diego Supercomputer Center, University of California San Diego, La Jolla, CA 92093, USA · The Scripps Research Institute, La Jolla, CA 92037, USA · Amentum, Space Biosciences Division, NASA Ames Research Center, Moffett Field, CA 94035, USA +3
GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering
May 28, 2026Xin Sun, Jianan Xie, Zhongqi Chen +6Agentic RL Knowledge Graph Question Answering
University of Science and Technology of China · 2NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences · 3ShanghaiTech University +1
Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
May 26, 2026Changqing Su, Yu Ding, Zuhong Lin +4KG Construction Multi-Agent LLM Systems
Hunan Key Laboratory of Carbon Neutrality and Intelligent Energy, School of New Energy and Environment, Hunan University of Technology and Business, Changsha 410205, P.R. China · Aerospace Kaitian Environmental Technology Co., Ltd., Changsha 410315, P.R. China · School of Energy Science and Engineering, Central South University, Changsha2026 410083, P.R. China
Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
May 26, 2026Madhulatha Mandarapu, Sandeep KunkunuruLLM Grounding Text-to-Cypher
VaidhyaMegha Private Limited, India

Jul 20, 2026, cs.DBJ/K move · Enter open · S save

Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation

Blake G. Fitch, Cato Elia Kurtz

Max Planck Institute for Biological Cybernetics Tübingen, Germany

Knowledge Representation Knowledge Graph Question Answering Natural Language to SPARQL

Open paper AskPDF arXiv

Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata. We show that when domain vocabulary and semantics are captured in a well-designed Web Ontology Language (OWL) ontology, Large Language Models (LLMs) can generate accurate structured queries zero-shot, without task-specific fine-tuning, retrieval augmentation, or multi-agent orchestration. We present the Natural Language Knowledge Graph Query (NLKGQ) system, a framework and development process that enables natural language access to metadata in such archives. The framework includes a web interface that helps researchers pose natural language questions, which a domain-agnostic harness translates to SPARQL via an LLM and executes against a knowledge graph. The development process begins with capturing domain vocabulary and semantics in a formal OWL ontology. Domain-specific code then extracts metadata from archive sources and imports it into a knowledge graph defined by the ontology. Both are designed for reuse across domains. We demonstrate the system on metadata derived from a large-scale neuroimaging research archive, evaluating multiple LLMs and ontology representations. The best configurations achieve 100% accuracy on a 21-question competency and regression test set developed with domain experts. An ablation study across eight ontology representations reveals that readable entity names and semantic annotations are the dominant factors in accuracy, more significant than model choice or prompt engineering. We also compare SPARQL to an auto-generated SQL database as query backends, showing that OWL's structural features provide a substantial advantage over SQL DDL for LLM-driven query generation. Our demonstration domain requires local LLMs on modest institutional hardware to address privacy concerns for human subject data.

Momentum

Related topics

Latest papers 91