调参优化ChatGPT，让机器翻译更富创意。
Optimising ChatGPT for creativity in literary translation: A case study from English into Dutch, Chinese, Catalan and Spanish
- 用最少指令+温度1.0，激发翻译创意
- 在西、荷、中语种上优于DeepL
- 虽不如人工译文，但可辅助文学翻译
本研究考察了ChatGPT在六种不同配置下，针对英译荷、中、加泰罗尼亚语和西班牙语四类文学文本的翻译输出差异，重点关注创造力表现。通过在不同文本粒度、温度设置及提示策略下评估生成结果，并引入创造力评分公式进行量化分析。结果显示，使用最简提示‘将以下文本创造性地翻译成[TG]’配合温度1.0时，翻译效果最佳，在西班牙语、荷兰语和中文中优于DeepL。然而，无论何种配置，ChatGPT整体仍逊于人类译者。
原文摘要 · Abstract (English)
This study examines the variability of Chat-GPT machine translation (MT) outputs across six different configurations in four languages,with a focus on creativity in a literary text. We evaluate GPT translations in different text granularity levels, temperature settings and prompting strategies with a Creativity Score formula. We found that prompting ChatGPT with a minimal instruction yields the best creative translations, with "Translate the following text into [TG] creatively" at the temperature of 1.0 outperforming other configurations and DeepL in Spanish, Dutch, and Chinese. Nonetheless, ChatGPT consistently underperforms compared to human translation (HT).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。