The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translation

arXiv cs.CL Papers

Summary

This study investigates how prompt language and translation-theory-driven prompt design affect the quality of Spanish-Chinese journalistic translations produced by GPT-5.2, finding that theory-driven prompts improve style under expert evaluation despite automated metrics favoring baseline prompts.

arXiv:2607.03160v1 Announce Type: new Abstract: 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.
Original Article
View Cached Full Text

Cached at: 07/07/26, 04:37 AM

# The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translation
Source: [https://arxiv.org/abs/2607.03160](https://arxiv.org/abs/2607.03160)
[View PDF](https://arxiv.org/pdf/2607.03160)

> Abstract: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\.

## Submission history

From: Haohong Lai \[[view email](https://arxiv.org/show-email/48086053/2607.03160)\] **\[v1\]**Fri, 3 Jul 2026 09:59:36 UTC \(508 KB\)

Similar Articles

No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

arXiv cs.CL

Researchers from National Taiwan University propose replacing fixed translation-based prompting strategies in multilingual LLMs with lightweight learned classifiers that route each instance to either native or translation-based prompting. Their analysis across 10 languages and 4 benchmarks shows no single strategy is universally optimal, with translation benefiting low-resource languages most, and the learned routing achieving statistically significant improvements over fixed strategies.

Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution

arXiv cs.CL

Introduces PRIG, a gradient attribution method that localizes prompt ambiguity in large language models by training a linear probe to distinguish clear from ambiguous prompts and attributing the probe score to token representations in the residual stream, achieving strong performance on synthetic and human-written benchmarks.

Interpreting Style Representations via Style-Eliciting Prompts

arXiv cs.CL

This paper proposes a framework to interpret style representations by using style-eliciting prompts—natural language instructions that steer LLMs to generate text with specific stylistic attributes. The method outperforms baseline LLM prompting techniques in both describing and imitating writing styles.