{"slug": "the-role-of-prompt-language-and-translation-theory-driven-prompts-in-large-a-on", "title": "The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translation", "summary": "A study on GPT-5.2's Spanish-Chinese journalistic translations found that translation theory-driven prompts improved quality under expert evaluation, with the brief-oriented prompt scoring highest (MQM: 8.66 vs. 7.84), while automated metrics favored the baseline prompt. Prompt language had negligible impact, and unidiomatic style errors persisted across conditions.", "body_md": "arXiv:2607.03160v1 Announce Type: new\nAbstract: This study examines how prompt language and translation theory-driven prompt design influence the quality of Spanish-Chinese journalistic translations generated by GPT-5.2. A parallel corpus of four editorials from El Pais was translated under 48 experimental conditions (4 prompt types, 3 prompt languages, and 4 articles). Translation quality was assessed using BLEU and BERTScore-F1 for automated evaluation, alongside human evaluation based on the Multidimensional Quality Metrics (MQM) framework. Automated metrics identified the baseline prompt (BASE) as the best-performing condition, whereas human evaluation ranked the brief-oriented prompt (BRIEF) highest (MQM: 8.66 vs. 7.84), a reversal likely attributable to the single-reference constraint inherent in automated measures. Sub-error type analysis revealed that translation theory-driven prompts selectively reduced Awkward style errors, while Unidiomatic style errors persisted across conditions. Prompt language had a negligible impact under both evaluation paradigms. These results indicate that translation theory-driven prompts can yield measurable quality gains under expert evaluation of journalistic translations, although their pedagogical implications for language learners remain suggestive and require validation through user-based studies.", "url": "https://wpnews.pro/news/the-role-of-prompt-language-and-translation-theory-driven-prompts-in-large-a-on", "canonical_source": "https://arxiv.org/abs/2607.03160", "published_at": "2026-07-07 04:00:00+00:00", "updated_at": "2026-07-07 04:02:26.664928+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research"], "entities": ["GPT-5.2", "El Pais", "BLEU", "BERTScore-F1", "Multidimensional Quality Metrics"], "alternates": {"html": "https://wpnews.pro/news/the-role-of-prompt-language-and-translation-theory-driven-prompts-in-large-a-on", "markdown": "https://wpnews.pro/news/the-role-of-prompt-language-and-translation-theory-driven-prompts-in-large-a-on.md", "text": "https://wpnews.pro/news/the-role-of-prompt-language-and-translation-theory-driven-prompts-in-large-a-on.txt", "jsonld": "https://wpnews.pro/news/the-role-of-prompt-language-and-translation-theory-driven-prompts-in-large-a-on.jsonld"}}