MT-Bench
June 2023
80 multi-turn questions judged by GPT-4. Showed that a strong model can grade chat quality about as well as people.
Connections
No links yet. This entry came from a dataset and has not been written up.
Sources: AI4U editorial.
June 2023
80 multi-turn questions judged by GPT-4. Showed that a strong model can grade chat quality about as well as people.
No links yet. This entry came from a dataset and has not been written up.
Sources: AI4U editorial.