Translation Errors and Post-editing Strategies in ChatGPT-assisted Translation of Chinese Political Texts: A Case Study of The Report on China’s Right to Development

Abstract

Large language models are increasingly being incorporated into translation workflows, yet their performance in politically sensitive texts remains underexplored. Political discourse poses particular challenges for machine translation because it relies heavily on specialized terminology, ideological meanings, and context-dependent expressions. Drawing on Chapter Three of The Report on China’s Right to Development, this paper examines translation errors in ChatGPT-generated output through a comparison with revised human translations. The analysis identifies three recurring problem areas: unnatural linguistic choices, weak information organization, and non-standard rendering of political terms. These problems are traced to limitations in probabilistic text generation, insufficient domain-specific knowledge, and incomplete contextual interpretation. To address them, three post-editing strategies are proposed: register adjustment, structural reorganization, and terminology standardization. The findings suggest that while ChatGPT is capable of producing fluent drafts, high-quality translation of political texts still depends on human expertise. The study highlights the continuing importance of post-editing in ensuring linguistic accuracy, conceptual precision, and discourse appropriateness in AI-assisted political translation.