Source URL: https://simonwillison.net/2025/Feb/2/workflow-for-translation/#atom-everything
Source: Simon Willison’s Weblog
Title: A professional workflow for translation using LLMs
Feedly Summary: A professional workflow for translation using LLMs
Tom Gally is a professional translator who has been exploring the use of LLMs since the release of GPT-4. In this Hacker News comment he shares a detailed workflow for how he uses them to assist in that process.
Tom starts with the source text and custom instructions, including context for how the translation will be used. Here’s an imaginary example prompt, which starts:
The text below in Japanese is a product launch presentation for Sony’s new gaming console, to be delivered by the CEO at Tokyo Game Show 2025. Please translate it into English. Your translation will be used in the official press kit and live interpretation feed. When translating this presentation, please follow these guidelines to create an accurate and engaging English version that preserves both the meaning and energy of the original: […]
It then lists some tone, style and content guidelines custom to that text.
Tom runs that prompt through several different LLMs and starts by picking sentences and paragraphs from those that form a good basis for the translation.
As he works on the full translation he uses Claude to help brainstorm alternatives for tricky sentences:
When I am unable to think of a good English version for a particular sentence, I give the Japanese and English versions of the paragraph it is contained in to an LLM (usually, these days, Claude) and ask for ten suggestions for translations of the problematic sentence. Usually one or two of the suggestions work fine; if not, I ask for ten more. (Using an LLM as a sentence-level thesaurus on steroids is particularly wonderful.)
He uses another LLM and prompt to check his translation against the original and provide further suggestions, which he occasionally acts on. Then as a final step he runs the finished document through a text-to-speech engine to try and catch any “minor awkwardnesses" in the result.
I love this as an example of an expert using LLMs as tools to help further elevate their work. I’d love to read more examples like this one from experts in other fields.
Tags: translation, generative-ai, hacker-news, ai, llms
AI Summary and Description: Yes
Summary: The text provides a detailed account of how a professional translator utilizes Large Language Models (LLMs) to enhance the translation process. It highlights the innovative integration of AI technology in human workflows, which is particularly relevant for professionals in AI and language processing fields.
Detailed Description: The content focuses on Tom Gally’s workflow for translation using LLMs like GPT-4 and Claude. It showcases how the translator leverages AI to improve accuracy and efficiency in translating complex documents, specifically emphasizing the role of custom prompts and iterative feedback.
– **Workflow Overview**:
– Initiates with a detailed prompt, including context relating to the specific document (e.g., product launch presentation).
– Sets clear guidelines for tone and style to inform the AI about the desired outcome.
– **Process Steps**:
– Runs initial prompts through multiple LLMs to derive a substantive translation basis.
– Employs LLMs for brainstorming alternatives when encountering difficult sentences—effectively using AI as a “sentence-level thesaurus.”
– Checks the quality of the translation against the original text using another LLM, facilitating further refinements.
– Conducts a final review of the document through a text-to-speech engine to identify any awkward phrasing or minor issues.
– **Key Insights**:
– Demonstrates a practical application of AI in professional fields, showcasing how technology can augment human expertise.
– Highlights the importance of clear guidelines and multiple iterations in achieving high-quality translations.
– Encourages further exploration of AI applications across various fields for enhanced workflows.
This example of integrating LLMs in translation work exemplifies a significant advancement in the role of AI in language services, providing valuable insights for professionals interested in the convergence of AI, language processing, and workflow optimization.