concept

KBQA

Also known as: Knowledge Graph-based Question Answering

Facts (19)

Sources

LLM-KG4QA: Large Language Models and Knowledge Graphs for ... github.com GitHub 8 facts

referenceThe paper 'The Value of Semantic Parse Labeling for Knowledge Base Question Answering' was published at ACL in 2016, utilizes the WebQSP dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'Benchmarking Large Language Models in Complex Question Answering Attribution using Knowledge Graphs' was published on arXiv in 2024, utilizes the CAQA dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'Automatic Question-Answer Generation for Long-Tail Knowledge' was published at KnowledgeNL@KDD in 2023, utilizes the Long-tail QA dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail Knowledge' was published on arXiv in 2024, utilizes the CR-LT-KGQA dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'BioASQ-QA: A manually curated corpus for Biomedical Question Answering' was published in Scientific Data in 2023, utilizes the BioASQ-QA dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'CPAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering' was published at ACL Findings in 2024, utilizes the TemporalQA dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering' was published at NeurIPS in 2024, utilizes the GraphQA dataset, and is categorized under KBQA and KGQA.

referenceThe paper 'HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering' was published at EMNLP in 2018, utilizes the HotpotQA dataset, and is categorized under KBQA and KGQA.

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 7 facts

referenceThe ODA method, proposed by Sun et al. in 2024, uses ODA-based knowledge graph retrieval with GPT-4 and GPT-3.5 models to perform KBQA tasks, evaluated using Hits@1 and Acc metrics on the QALD10-en dataset.

referenceLongRAG, as described by Zhao et al. (2024a), utilizes domain-specific fine-tuning for RAG and CoT-guided filtering with models including ChatGLM3-6B, Qwen1.5-7B, Vicuna-v1.5-7B, Llama-3-8B, GPT-3.5-Turbo, and GLM-4, applied to Wikidata for KBQA and Multi-hop QA tasks.

referenceThe LEGO-GraphRAG method, proposed by Cao et al. in 2024, utilizes modular graph RAG with Qwen2-72B and Sentence Transformer models, incorporating the Freebase knowledge graph to perform KBQA and CWQ tasks on the WQSP, CWQ, and GrailQA datasets, evaluated using R, F1, and Hits@1 metrics.

referenceThe InteractiveKBQA method, proposed by Xiong et al. in 2024, uses Multi-turn Interaction for Observation and Thinking with GPT-4-Turbo, Mistral-7B, and Llama-2-13B models and Freebase, Wikidata, and Movie KG knowledge graphs for KBQA and domain-specific QA, evaluated using F1, Hits@1, EM, and Acc metrics on the WQSP, CWQ, KQA Pro, and MetaQA datasets.

referenceThe KG-CoT method, proposed by Zhao et al. in 2024, uses chain-of-thought-based joint reasoning between knowledge graphs and LLMs (GPT-4, GPT-3.5-Turbo, Llama-7B, Llama-13B) to perform KBQA and multi-hop QA tasks, evaluated using Acc and Hit@K metrics on WQSP, CWQ, SQ, and WQ datasets.

referenceThe ToG method, proposed by Sun et al. in 2024, uses beam-search-based retrieval and LLM agents with GPT-3.5-Turbo, GPT-4, and Llama-2-70B-Chat models to perform KBQA and open-domain QA tasks, evaluated using Hits@1 on CWQ, WQSP, GrailQA, QALD10-en, and WQ datasets.

referenceThe SR method, proposed by Zhang et al. in 2022, utilizes a trainable subgraph retriever and fine-tuning with the RoBERTa-base language model and dataset-inherent knowledge graphs to perform KBQA tasks, evaluated using Hits@1 and F1 metrics on WQSP and CWQ datasets.

KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org arXiv Mar 18, 2025 3 facts

claimKnowledge Graph-based Question Answering (KBQA) has been applied across various domains, including text understanding and fact-checking.

referenceApproaches to Knowledge Graph-based Question Answering (KBQA) are categorized into Information Retrieval (IR)-based methods and Semantic Parsing (SP)-based methods. IR-based methods directly retrieve information from knowledge graph databases and use the returned knowledge to generate answers, whereas SP-based methods generate logical forms for queries, which are then used for knowledge retrieval.

claimLarge Language Models (LLMs) enhance performance in Knowledge Graph-based Question Answering (KBQA) tasks, which leverage external knowledge bases to answer user queries.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 1 fact

referenceMEG and LLM-KGMQA enhance knowledge graph-based question answering by integrating graph embeddings from a pre-trained knowledge graph encoder into a large language model and using the model's reasoning capabilities to refine query interpretations.