Lists
Lists
Svintsova, Evgeniya, Al-Sudani, Sahar and Ghanem, Mohamed Chahine (2025) Assessment of integrating LLM in websites localisation service. In: 8th Conference on Cloud and Internet of Things, 29-31 October 2025, London, UK. (In Press)
This paper introduces a novel integration of Large Language Models (LLMs) into website localisation services through a prompt-engineering-first approach. Traditional localisation methodologies - human translation, machine translation, and hybrid approaches - have established trade-offs between quality, cost, and efficiency. The emergence of advanced LLMs offers a potential paradigm shift in addressing these challenges. The research presented explores how focusing on prompt engineering rather than post-translation editing can fundamentally transform localisation workflows while maintaining high-quality outputs. Drawing on recent research in prompt engineering and machine translation efficacy, the paper establishes a theoretical framework for LLM implementation in localisation services. A practical case study involving the localisation of a cross-platform application demonstrates the implementation of this approach, including technical architecture, prompt design strategies, and testing methodologies. The findings indicate that LLM-powered localisation with well-engineered prompts can deliver superior quality to specialised translation services while offering significant advantages in maintaining marketing tone, reducing implementation complexity, and supporting broader content creation needs across languages. The analysis extends beyond theoretical considerations to provide an innovative decision framework for selecting appropriate localisation tools based on specific project requirements. The research concludes that for projects with marketing-focused content and moderate translation volume, the LLM approach with focused prompt engineering represents a superior solution compared to traditional translation services and dedicated localisation platforms.
Available under License Creative Commons Attribution 4.0.
Download (571kB) | Preview
 |
View Item |