Will large language models become the state of the art for machine translation in 2023?

Resolves the same as the original on Metaculus.

Resolution criteria

This question resolves as Yes if the official results of the WMT23 General Machine Translation Task show that for the majority of evaluated language pairs, the top cluster of systems contains a system that is directly based on a large language model.

Fine print and additional background information can be found on Metaculus.

Once the original resolves, its resolution will be applied to this market automatically. Trustworthy-ish users are encouraged to resolve this market before then if the outcome is known and unambiguous. Feel free to ping @jskf to request early resolution or to report issues.