RefKG System to Fact-Checking and Query Resolution (QR) with Knowledge Graphs and Large Language Models (LLMs)
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V7I2P118Keywords:
Digital Information, QR Code, Query Resolution (QR), Fact-Checking, Knowledge Graphs (Kgs), Machine Learning (ML), Large Language Models (Llms), Refkg SystemAbstract
The processes of Fact-checking and the use of knowledge-driven resolution are inevitable to increase the reliability of the information obtained from knowledge graphs of large sizes. The paper presents RefKG as a knowledge-based framework for enhancing fact verification while performing multi-hop reasoning through the combination of language models and structured knowledge graphs. The system improves knowledge representation with α = 0.6 as its confidence threshold while it enhances fact retrieval through combinations of Top-K reasoning with multi-task learning approaches. An evaluation of RefKG takes place on benchmark datasets WebQSP, MetaQA and FactKG by measuring its performance against current fact-checking models. The results establish that RefKG surpasses existing models by reaching 85.2% Hits@1 accuracy on WebQSP alongside an average 98.8% accuracy on MetaQA. Additionally, experiments on FactKG show improvements in fact verification accuracy and retrieval efficiency. The results illustrate that RefKG demonstrates high efficiency through its knowledge-based methodology, thus establishing it as a dependable system for automated fact-checking as well as complex query resolution
References
[1] H. Bashir, “Leveraging technology to communicate sustainability-related product information: Evidence from the field,” J. Clean. Prod., 2022, doi: 10.1016/j.jclepro.2022.132508.
[2] S. Dodda, N. Kamuni, P. Nutalapati, and J. R. Vummadi, “Intelligent Data Processing for IoT Real-Time Analytics and Predictive Modeling,” in 2025 International Conference on Data Science and Its Applications (ICoDSA), IEEE, Jul. 2025, pp. 649–654. doi: 10.1109/ICoDSA67155.2025.11157424.
[3] S. R. Kumar, M. Shukla, and N. Patel, “Cyber Security Detecting And Alerting Device,” 2024.
[4] S. Kilaru, V. S. R. Yarlagadda, and M. B. Nagaraja, “AI-Augmented Block-Sketch Hybrid Compression: Enabling Semantic Query Processing on Compressed Data,” in 2026 IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA: IEEE, 2026, pp. 0966–0972, Jan. doi: 10.1109/CCWC67433.2026.11393750.
[5] N. Urbani, S. Modha, and G. Pasi, “Retrieving Semantics for Fact-Checking: A Comparative Approach using CQ (Claim to Question) & AQ (Answer to Question),” FEVER 2024 - 7th Fact Extr. Verif. Work. Proc. Work., pp. 37–45, 2024.
[6] S. Pawar, G. Patil, K. Patel, P. Pawar, S. Khedkar, and B. More, “Falsified News Detection Using Deep Learning Approach,” in 2021 Asian Conference on Innovation in Technology (ASIANCON), 2021, pp. 1–5. doi: 10.1109/ASIANCON51346.2021.9544585.
[7] S. Pahune and Z. Akhtar, “Transitioning from MLOps to LLMOps: Navigating the Unique Challenges of Large Language Models,” Information, vol. 16, no. 2, p. 87, Jan. 2025, doi: 10.3390/info16020087.
[8] D. Quelle and A. Bovet, “The perils and promises of fact-checking with large language models,” Front. Artif. Intell., 2024, doi: 10.3389/frai.2024.1341697.
[9] P. Choudhary, R. Choudhary, and S. Garaga, “Enhancing Training by Incorporating ChatGPT in Learning Modules : An Exploration of Benefits , Challenges , and Best Practices,” Int. J. Innov. Sci. Res. Technol., vol. 9, no. 11, 2024, doi: 10.5281/zenodo.14272874.
[10] S. S. Saisuman Singamsetty, Hy-Search: A Hybrid Retrieval-Augmented Framework for Factual and Context-Aware Enterprise Knowledge Discovery. 2025. doi: 10.2991/978-94-6463-978-0_37.
[11] S. Vaithilingam and S. A. M. Shankar, “Enhancing Security in QR Code Technology Using AI: Exploration and Mitigation Strategies,” Int. J. Intell. Sci., vol. 14, no. 02, pp. 49–57, 2024, doi: 10.4236/ijis.2024.142003.
[12] S. Pahune and M. Chandrasekharan, “Several Categories of Large Language Models (LLMs): A Short Survey,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 11, no. 7, pp. 615–633, 2023, doi: 10.22214/ijraset. 2023.54677.
[13] B. Krishnan, S. Perla, S. Maddela, and R. Lingam, “Adaptive Multi-Cloud Infrastructure for CRM Analytics: Real-Time ML and Data Sync with LLMs,” in 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN), IEEE, Nov. 2025, pp. 1–8. doi: 10.1109/GCWCN66157.2025.11448404.
[14] R. Rao Thallada and N. Alapati, “Privacy and Cybersecurity Convergence: GRC Controls for Data Protection,” Journal Bus. Manag. Stud., vol. 8, no. 5, pp. 42–48, March, 2026, doi: 10.32996/jbms.
[15] R. Kumar, “RefKG: A Knowledge-Driven System for Fact-Checking and Query Resolution Using Knowledge Graphs,” in Recent Advancements in Artificial Intelligence, R. Nayak, N. Mittal, A. Khunteta, and M. Kumar, Eds., Singapore: Springer Nature Singapore, 2025, pp. 405–427.
[16] M. Du, “QR code resolution improvement based on Super-Resolution Generative Adversarial Network,” Appl. Comput. Eng., vol. 51, no. 1, pp. 6–13, Mar. 2024, doi: 10.54254/2755-2721/51/20241147.
[17] H. Almousa, A. Almarzoqi, A. Alassaf, G. Alrasheed, and S. Alsuhibany, “QR Shield: A Dual Machine Learning Approach Towards Securing QR Codes,” Int. J. Comput. Digit. Syst., vol. 15, pp. 887–898, 2024, doi: 10.12785/ijcds/160164.
[18] A. S. Rafsanjani, N. B. Kamaruddin, H. M. Rusli, and M. Dabbagh, “QsecR: Secure QR Code Scanner According to a Novel Malicious URL Detection Framework,” IEEE Access, 2023, doi: 10.1109/ACCESS.2023.3291811.
[19] E. Lazarski, M. Al-Khassaweneh, and C. Howard, “Using NLP for Fact Checking: A Survey,” Designs, vol. 5, no. 3, p. 42, Jul. 2021, doi: 10.3390/designs5030042.
[20] L. Huo, J. Zhu, P. K. Singh, and P. A. Pavlovich, “Research on QR image code recognition system based on artificial intelligence algorithm,” J. Intell. Syst., 2021, doi: 10.1515/jisys-2020-0143.
[21] A. Immadisetty, “Edge Analytics vs. Cloud Analytics: Tradeoffs in Real-Time Data Processing,” J. Recent Trends Comput. Sci. Eng., vol. 13, no. 1, pp. 42–52, 2016.
[22] M. Al-Tawil, V. Dimitrova, D. Thakker, and B. Abu-Salih, “Emerging Exploration Strategies of Knowledge Graphs,” IEEE Access, 2023, doi: 10.1109/ACCESS.2023.3308514.
[23] S. R. Thota and S. Arora, “Collaborative Filtering and Knowledge Graphs for Data Discovery,” Int. Res. J. Mod. Eng. Technol. Sci., vol. 06, no. 05, 2024, doi: 10.56726/IRJMETS56957.
[24] Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, “Learning entity and relation embeddings for knowledge graph completion,” in Proceedings of the National Conference on Artificial Intelligence, 2015. doi: 10.1609/aaai.v29i1.9491.
[25] [25] P. Lewis et al., “Retrieval-augmented generation for knowledge-intensive NLP tasks,” Adv. Neural Inf. Process. Syst., vol. 2020-Decem, 2020.
[26] A. Saxena, A. Tripathi, and P. Talukdar, “Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Stroudsburg, PA, USA: Association for Computational Linguistics, 2020, pp. 4498–4507. doi: 10.18653/v1/2020.acl-main.412.
[27] J. Jiang, K. Zhou, W. X. Zhao, and J.-R. Wen, “UNIKGQA: Unified Retrieval and Reasoning for Solving Multi-Hop Question Answering Over Knowledge Graph,” ICLR, pp. 1–18, 2023, doi: 10.48550/arXiv. 2212.00959.
[28] H. Sun, B. Dhingra, M. Zaheer, K. Mazaitis, R. Salakhutdinov, and W. Cohen, “Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Stroudsburg, PA, USA: Association for Computational Linguistics, 2018, pp. 4231–4242. doi: 10.18653/v1/D18-1455.
