Knowledge Graph Question Answering

Also known as KGQA

Knowledge Graph Question Answering (KGQA) connects questions to entities and relations in a graph, then returns answers supported by its structured facts. Common approaches translate questions into SPARQL or logical forms, retrieve and traverse multi-hop paths, or combine graph neural networks and symbolic rules with large language models and retrieval-augmented generation. Benchmarks such as WebQSP, ComplexWebQuestions, and GrailQA test query execution, compositional reasoning, and generalization, while newer evaluations examine temporal, biomedical, and incomplete-graph settings. A central challenge is ensuring that answers are both accurate and grounded in relevant evidence, especially when graphs are sparse or noisy and benchmark questions may not require genuine multi-hop reasoning.

Latest papers

169 papers20 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

RADAR: Reasoning as Discrimination with Aligned Representations for LLM-based Knowledge Graph Reasoning
Feb 25, 2026Bo Xue, Yuan Jin, Luoyi Fu +2Graph Reasoning KG Completion
Shanghai Jiao Tong University, Shanghai, China
Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
Feb 25, 2026Shiqi Yan, Yubo Chen, Ruiqi Zhou +8LLM Reasoning with Graphs Knowledge Graph Question Answering
Zhongguancun Laboratory, Beijing, China · Department of Electronic Engineering, Tsinghua University, Beijing, China · Ant International, Ant Group, Hangzhou, Zhejiang, China +1
Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering
Feb 23, 2026Wuzhenghong Wen, Bowen Zhou, Jinwen Huang +5Knowledge Graph Question Answering Temporal QA
School of Internet of Things, Nanjing University of Posts and Telecommunications · Faculty of Medicine & Health, University of New South Wales, Sydney, Australia · Beijing Information Science and Technology University +2
VIRAASAT: Traversing Novel Paths for Indian Cultural Reasoning
Feb 20, 2026Harshul Raj Surana, Arijit Maji, Aryan Vats +3Cultural Knowledge in Language Models Multi-Hop QA
AI Institute, University of South Carolina, USA · Indian Institute of Technology Patna, India
Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
Feb 20, 2026Jash Rajesh Parekh, Wonbin Kweon, Joey Chan +7Biomedical QA Medical Reasoning
University of Illinois Urbana-Champaign · National Institutes of Health
NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
Feb 17, 2026Rong Fu, Yang Li, Zeyu Zhang +7Knowledge Graph Question Answering Multi-Hop QA
Independent Researcher
The Wikidata Query Logs Dataset
Feb 16, 2026Sebastian Walter, Hannah BastKnowledge Graph Question Answering Knowledge Graphs
University of Freiburg, Department of Computer Science, Freiburg im Breisgau, Germany
HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation
Feb 16, 2026Wen-Sheng Lien, Yu-Kai Chan, Hao-Lung Hsiao +5Hypergraph-Based RAG Retrieval-Augmented Generation
National Yang Ming Chiao Tung University, Hsinchu, Taiwan · E.SUN Bank, Taipei, Taiwan · National Kaohsiung Normal University, Kaohsiung, Taiwan
UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
Jan 28, 2026Dobrik Georgiev, Kheeran K. Naidu, Alberto Cattaneo +3Multi-Hop QA LLM Reasoning with Graphs
Graphcore Research
GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning
Jan 24, 2026Yuyang Bai, Zhuofeng Li, Ping Nie +3LLM Reasoning with Graphs RL for Language Model Reasoning
Texas A&M University · University of Waterloo · Lambda +1
SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions
Dec 16, 2025Panayiotis Smeros, Vincent Emonet, Ruijie Wang +2Knowledge Graph Question Answering Natural Language to SPARQL
SIB Swiss Institute of Bioinformatics, Switzerland · SIB Swiss Institute of Bioinformatics and University of Zurich, Switzerland
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
Dec 10, 2025Xin Sun, Zhongqi Chen, Xing Zheng +6LLM Grounding RL for Language Model Reasoning
University of Science and Technology of China, Hefei, China · Independent · Institute of Automation, Chinese Academy of Sciences, Beijing, China.
Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
Nov 6, 2025Alberto Cattaneo, Carlo Luschi, Daniel JustusGraph Retrieval-Augmented Generation Synthetic Benchmark Generation
Graphcore AI Research
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Nov 6, 2025Yuanning Cui, Zequn Sun, Wei Hu +1Multi-Hop QA LLM Grounding
School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China · National Institute of Healthcare Data Science, Nanjing University, Nanjing 210093, China +2
CQD-SHAP: Explainable Complex Query Answering via Shapley Values
Oct 17, 2025Parsa Abbasi, Stefan HeindorfNeuro-Symbolic Reasoning Knowledge Graph Question Answering
Department of Computer Science, Paderborn University, Germany
Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
Oct 17, 2025Jinliang Liu, Jiale Bai, Shaoning ZengMulti-Hop QA Graph Retrieval-Augmented Generation
Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou, Zhejiang, China · School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China
Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection
Feb 20, 2025Han Zhang, Langshi Zhou, Hanfang YangLLM Reasoning with Graphs Knowledge Graph Question Answering
Center for Applied Statistics, Renmin University of China · School of Statistics, Renmin University of China
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
Feb 17, 2025Runxuan Liu, Bei Luo, Jiaqi Li +5LLM Reasoning with Graphs Graph-Based Retrieval
Harbin Institute of Technology, Harbin, China · Beijing University of Posts and Telecommunications, Beijing, China · Joint Laboratory of HIT and iFLYTEK, Beijing, China +2
Is Complex Query Answering Really Complex?
Oct 16, 2024Cosimo Gregucci, Bo Xiong, Daniel Hernandez +4Knowledge Graph Question Answering Knowledge Graphs
Institute for Artificial Intelligence, University of Stuttgart, Germany · Stanford University · School of Informatics University of Edinburgh Edinburgh, UK +1

Feb 25, 2026J/K move · Enter open · S save

RADAR: Reasoning as Discrimination with Aligned Representations for LLM-based Knowledge Graph Reasoning

Bo Xue, Yuan Jin, Luoyi Fu, Jiaxin Ding+1

Shanghai Jiao Tong University, Shanghai, China

Graph Reasoning KG Completion LLMs for Graph Learning Knowledge Graph Question Answering

Open paper AskPDF arXiv

Knowledge graph reasoning (KGR) infers missing facts, with recent advances increasingly harnessing the semantic priors and reasoning abilities of Large Language Models (LLMs). However, prevailing generative paradigms are prone to memorizing surface-level co-occurrences rather than learning genuine relational semantics, limiting out-of-distribution generalization. To address this, we propose RADAR, which reformulates KGR from generative pattern matching to discriminative relational reasoning. We recast KGR as discriminative entity selection, where reinforcement learning enforces relative entity separability beyond token-likelihood imitation. Leveraging this separability, inference operates directly in representation space, ensuring consistency with the discriminative optimization and bypassing generation-induced hallucinations. Across four benchmarks, RADAR achieves 5-6% relative gains on link prediction and triple classification over strong LLM baselines, while increasing task-relevant mutual information in intermediate representations by 62.9%, indicating more robust and transferable relational reasoning.