Explainable Large Language Model for Islamic and Humanities Sciences Based on Knowledge Graphs

Document Type : Original Article

Authors

1 Assistant Professor, Information Dissemination and Knowledge Exchange Department, Islamic Science and Culture Research Institute, Qom, Iran

2 B.A., Department of Knowledge and Information Science, University of Qom, Qom, Iran.

Abstract

Purpose: This research explores the challenges and opportunities associated with integrating knowledge graphs and large language models in the fields of Islamic studies and the humanities. The primary motivation is the complexity and diversity of concepts and categories within these fields. Religious and humanistic concepts inherently possess multiple dimensions and layers, demanding innovative and efficient analytical approaches. Knowledge graphs are powerful tools for organizing information and representing relationships between concepts. They clarify and visualize intricate connections, enabling researchers to easily understand the interrelations among various concepts. The core objective of this study is to present a framework that integrates these two concepts within Islamic and humanities studies, thereby enabling a more precise and efficient analysis of Islamic and humanistic concepts.
Method: This research is a conceptual study that employs an analytical approach. Data were collected through a systematic literature review, which identified key and fundamental concepts. Existing resources in both the knowledge graph and large language model domains were purposefully selected for analysis.
Findings: The primary finding of this research is the development of an innovative framework that integrates knowledge graphs and large language models to analyze and infer concepts within Islamic and humanities studies. Knowledge graphs serve as tools for organizing information and representing relationships between concepts, helping to clarify and visualize intricate connections among them. Furthermore, large language models can process natural language and extract meaningful information from texts. The integration of these two approaches can foster the creation of innovative frameworks for data analysis and inference within the field of religious studies.
Conclusion: The integration of knowledge graphs and large language models represents a novel and efficient approach to analyzing and inferring complex concepts in Islamic and humanities studies. The proposed framework can serve as a model for future research and the development of intelligent systems in these fields, thereby enhancing the research and analysis processes in Islamic and humanities studies.

Keywords

Main Subjects

References

Abaskohi, A., Baruni, S., Masoudi, M., Abbasi, N., Babalou, Mh., Edalat, A., Kamahi, S. & et al. (2024). Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT. arXiv. https://doi.org/10.48550/arXiv.2404.02403
Binz, M. & Schulz, E. (2023). Turning large language models into cognitive models. arXiv.       
https://doi.org/10.48550/arXiv.2306.03917
Chen, Z., Singh, A.K. & Sra, M. (2023). LMExplainer: a Knowledge-Enhanced Explainer for Language Models. arXiv. https://doi.org/10.48550/arXiv.2303.16537
Confalonieri, R., Coba, L., Wagner, B. & Besold, T.R. (2020). A historical perspective of explainable Artificial Intelligence. WIRES Data Mining Know Discov, no. 11.         
https://doi.org/10.1002/widm.1391
Huang, J. & Chang, K.C.-C. (2023a). Towards Reasoning in Large Language Models: A Survey. arXiv. https://doi.org/10.48550/arXiv.2212.10403
Huang, S., Mamidanna, S., Jangam, S., Zhou, Y. & Gilpain, L.H. (2023b). Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations. arXiv.        
https://doi.org/10.48550/arXiv.2310.11207
Luo, H. & Specia, L. (2024). From Understanding to Utilization: A Survey on Explainability for Large Language Models. arXiv. https://doi.org/10.48550/arXiv.2401.12874
Mavrepis, P., Makridis, G., Fatouros, G., Koukos, V., Separdani, M.M. & Kyriazis, D. (2024). XAI for All: Can Large Language Models Simplify Explainable AI? arXiv preprint arXiv: 2401.11310.
Patel, S., Kane, H. & Patel, R. (2023). Building Domain-Specific LLMs Faithful To The Islamic Worldview: Mirage or Technical Possibility?. arXiv. https://doi.org/10.48550/arXiv.2312.06652
Rasti Meymandi, A., Hosseini, Z., Davari, S., Moshiri, A., Rahimi Golkhandan, S., Namdar, K., Feizi, N., Tavakoli-Targhi, M. & Khalvati, F. (2024). Opportunities for Persian Digital Humanities Research with Artificial Intelligence Language Models; Case Study: Forough Farrokhza. arXiv. https://doi.org/10.48550/arXiv.2405.06760
Shu, D., Chen, T., Jin, M., Zhang, Y., Zhang, C., Du, M. & Zhang, Y. (2024). Knowledge Graph Large Language Model (KG-LLM) for Link Prediction. arXiv.       
https://doi.org/10.48550/arXiv.2403.07311
Sullivan, D. (2020). A reintroduction to our Knowledge Graph and knowledge panels.
URL= https://blog.google/products/search/about-knowledge-graph-and-knowledge-panels
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cia, H., Wang, S. & Yin, D. (2024). Explainability for Large Language Models: A Survey. ACM Transactions on Intelligent Systems and Technology, 15(2). https://doi.org/10.1145/3639372
Zheng, Y., Koh, H.Y., Ju, J., Nguyen, A.T.N., May, L.T.,Webb, G.L. & Pan, S. (2023). Large Language Models for Scientific Synthesis, Inference and Explanation. arXiv.      
https://doi.org/10.48550/arXiv.2310.07984
 
Send comment about this article
CAPTCHA Image
Sciences and Techniques of Information Management
Volume 10, Issue 4
November 2024
Pages 7-38

Files

Share

How to cite

Statistics