←back to thread

Teuken-7B-Base and Teuken-7B-Instruct: Towards European LLMs (2024)

(arxiv.org)
246 points doener | 2 comments | 15 Apr 25 10:17 UTC | HN request time: 0.779s | source
Show context
ozgune ◴[15 Apr 25 12:12 UTC] No.43691597[source]▶
I had a related, but orthogonal question about multilingual LLMs.

When I ask smaller models a question in English, the model does well. When I ask the same model a question in Turkish, the answer is mediocre. When I ask the model to translate my question into English, get the answer, and translate the answer back to Turkish, the model again does well.

For example, I tried the above with Llama 3.3 70B, and asked it to plan me a 3-day trip to Istanbul. When I asked Llama to do the translations between English <> Turkish, the answer was notably better.

Anyone else observed a similar behavior?

replies(11): >>43691620 #>>43691751 #>>43691774 #>>43692427 #>>43692596 #>>43692803 #>>43692874 #>>43693906 #>>43695475 #>>43698229 #>>43698667 #
1. mdp2021 ◴[15 Apr 25 14:01 UTC] No.43692803[source]▶
Some studies are trying to ensure that the model reasons through abstractions instead of linguistic representations. (Of course the phenomenon of reasoning in substantially different quality depending on input language signals a fault - reasoning is beyond "spoken" language.)

In the past hours a related, seemingly important article appeared - see https://www.quantamagazine.org/to-make-language-models-work-...

replies(1): >>43693086 #
2. jmmcd ◴[15 Apr 25 14:18 UTC] No.43693086[source]▶
This important paper from Anthropic includes evidence that part (but only part) of reasoning is cross-lingual:

https://www.anthropic.com/research/tracing-thoughts-language...