AI Translation: Evaluating ChatGPT’s Reliability in Translating Arabic to English
Keywords:
Artificial Intelligence Translation, ChatGPT, Arabic-English Translation, Generative AIAbstract
The rapid advancement of generative artificial intelligence (AI) has transformed language translation by introducing adaptive, context-aware systems capable of producing human-like linguistic outputs. Among these systems, ChatGPT represents a significant development in AI-driven translation due to its large-scale language modeling capabilities and ability to interpret complex textual patterns. This research evaluates the reliability of ChatGPT in translating Arabic texts into English by examining translation accuracy, contextual preservation, semantic alignment, and limitations associated with generative AI-based language processing. The study adopts a conceptual analytical methodology based on existing research perspectives related to AI frameworks, computational simulation, prompt engineering, and intelligent system reliability. The investigation positions AI translation as an intelligent service architecture where input interpretation, contextual reasoning, and output generation influence overall performance. The findings indicate that ChatGPT provides strong translation capabilities for general Arabic-English conversion but faces challenges in handling cultural expressions, linguistic ambiguity, domain-specific terminology, and context-dependent meanings. The research highlights that reliability depends not only on model capability but also on effective interaction strategies, evaluation frameworks, and human oversight mechanisms. Drawing from developments in AI system design and intelligent automation, this study contributes a structured understanding of ChatGPT’s role as an AI translation assistant and identifies future opportunities for improving multilingual generative AI systems.
References
1. Sayyed, Z. (2025). Development of a Simulator to Mimic VMware vCloud Director (VCD) API Calls for Cloud Orchestration Testing. International Journal of Computational and Experimental Science and Engineering, 11(3). https://doi.org/10.22399/ijcesen.3480
2. Pai, D. (2025). Prompt Engineering Frameworks for Generative AI in Credit Analysis. https://doi.org/10.52783/jisem.v10i45s.9035
3. K. Bhat and G. Krishnan, "A Review of Agentic Artificial Intelligence: Power of Self-Driven AI in the Future of Financial Autonomy and Enhanced Customer Engagement," 2025 3rd International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Erode, India, 2025, pp. 1160-1165, doi: 10.1109/ICSCDS65426.2025.11167368.
4. S. S. Sravanthi Valiveti, "Evolution of ASP.NET to ASP.NET Core: Tools, Strategies, and Implementation Approaches," 2025 IEEE 2nd International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), Bangalore, India, 2025, pp. 1-7, doi: 10.1109/ICITEICS64870.2025.11341480.
5. Hebbar, K. S., Sharma, V., & Maheshkar, J. A. (2026). Edge-AI microservice orchestration for private, real-time generative FinTech applications. Future Technology, 5(2), 13–24. https://doi.org/10.55670/fpll.futech.5.2.2
6. Rashi, A. R., Gunukula, S., Anupriya, M., Jadhav, S. R., & Zarekar, M. (2025). Impact of Prophylactic Antibiotic Protocols in Cardiac Patients Undergoing Endodontic Surgery and Subsequent Prosthetic Treatment: A Comparative Study. Vascular and Endovascular Review, 8(14s), 168-174. 17(12).
