# Zouden we LLM's kunnen gebruiken om vertalingen te verbeteren?

**URL:** https://meta.discourse.org/t/could-we-use-llms-to-improve-translations/286027
**Category:** Feature
**Created:** [20 november 2023 om 03:08 UTC](https://meta.discourse.org/t/could-we-use-llms-to-improve-translations/286027 "2023-11-20T03:08:07Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![meglio](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/meglio/32/71444_2.png) [@meglio](https://meta.discourse.org/u/meglio)
#### Post date: [20 november 2023 om 03:08 UTC](https://meta.discourse.org/t/could-we-use-llms-to-improve-translations/286027/1 "2023-11-20T03:08:07Z")

</div>

Continuing the discussion from [Enable AI Bot](https://meta.discourse.org/t/enable-ai-bot/266012):

**Could we use LLMs to improve translations?** Possible application areas:

- find discrepancies in existing translations (terminology and language should match across the whole websige)
- make translations more consistent by answering translation-related questions, such as “where in the interface XXX is used, give me a couple of examples”
- extract the “community language” from top topics across, so that in site-specific translation overrides one could use the language specific and familiar to their community, optionally with some slang suggested by the LLM