Abstract Large language models (LLMs) have exhibited remarkable abilities in understanding and generating human language, which is applied in transferring languages. However, the translation of literary works presents unique challenges. The translation quality of literary works generated by LLMs is yet to be explored and tested. Therefore, this study aims to evaluate the quality of translations produced by various LLMs in comparison to a well-established human-translated work. The famous Chinese literary work Border Town by Shen Congwen was selected as the source text. ChatGPT 4, ChatGPT 4o, WXYY 4.0 Turbo, and Gemini were adopted as the models to process the translation. Jeffrey Kinkley’s translation was chosen as the human translation for comparison. This research employs Multidimensional Quality Metrics to evaluate translation quality by providing detailed error typologies. We focused on error analysis from three key dimensions of translation quality: accuracy, fidelity, and cultural appropriateness. The results showed that five types of errors were identified: mistranslation, omission, over-translation, cultural mistranslation, and discourse-level errors. Mistranslation has the top frequency in all models, omission occurs the most in Gemini, over translation and cultural mistranslation appear the most in GPT4. Discourse-level error occurred in WXYY 4.0 turbo the most. GPT-4o appears to yield comparatively higher translation quality under the MQM framework. The research reveals that literary translation by LLMs requires more specific training prompt strategies and human post-editing to improve its accuracy, fidelity, and cultural appropriateness.
Yang et al. (Sat,) studied this question.