Can GPT-4 translate literature?
Why Hacker News recommends it
Cited as an expert's first-hand evidence that GPT translation is near human quality for distant language pairs.
What it is
Tom Gally, a former professional translator and University of Tokyo professor, discusses in March 2023 whether GPT-4 and similar models could translate literary and popular fiction. He gives his assessment of Japanese-to-English quality.
Recommended by 0 HN commenters across 0 different months, 2023 to 2025.
What Hacker News said
Cites bumbledraven · 2023-03 · on “ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks”
Are you giving it multiple paragraphs to translate at once so that it has enough context for a good translation? If so, would you mind sharing a sample input and output that you found unsatisfactory? In "Can GPT-4 translate literature?" (Mar 18, 2023) [ [this video] ], Tom Gally, a former professional translator and current professor at the University of Tokyo, said: > …the point is, to my eye at least, the the basic quality of the translation [from Japanese to English] is as good as a human might do, and with some relatively mild editing by a sensitive human editor, it could be turned into a novel that would be readable and enjoyable.
Cites og_kalu · 2023-09 · on “”
>about machine translation and looked at some results of translating between English and French. It was difficult to find any fault with the translation. This has never been the case for distant language pairs till GPT. That is a pretty big change. [this video]
Cites og_kalu · 2023-09 · on “”
>but nobody in the very well funded translation industry has a GPT powered translation engine for the key reason that it's not ready for production. Translator for 20 years talking about using GPT for Japanese-English. [this video] [LINK]
Cites tkgally · 2025-02 · on “Notes on OpenAI o3-mini”
As I explained in a sister comment, it is not possible to rate translation quality objectively, as opinions and positions about what constitutes a good translation vary. But in my tests of reasoning models since the release of o1-preview, they have not seemed as reliable as the straight nonreasoning versions of ChatGPT, Claude, or Gemini. The translation process itself usually doesn’t seem to require the kind of multistep thinking those reasoning models can be good at. For more than a year, regular LLMs, when properly prompted, have been able to produce translations that would be indistinguishable from those of some professional translators for some types of translation. General-purpose LLMs