LLMs are sequence-to-sequence like language translation models, were invented for the purpose of language models, and if you were making a translator today it would be structured like an LLM but might be small and specialized.

For practical purposes though I like being able to have a conversation with a language translator: if I was corresponding with somebody in German, French, Spanish, related European languages or Japanese I would expect to say:

  I'm replying to ... and want to say ... in a way that is compatible in tone

and then get something that I can understand enough to say

  I didn't expect to see ... what does that mean?

And also run a reverse translation against a different model, see that it makes sense, etc. Or if I am reading a light novel I might be very interested in

  When the story says ... how is that written in Japanese?