Llama + 1M BT + gold

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Grammatical Error CorrectiononEstGEC-L2
F0.5· uses extra data· 2024-03-08
69.97
SOTA
To Err Is Human, but Llamas Can Learn It Too arXiv:2403.05493
Grammatical Error CorrectiononFalko-MERLIN
F0.5· uses extra data· 2024-03-08
76.75
SOTA
To Err Is Human, but Llamas Can Learn It Too arXiv:2403.05493
Grammatical Error CorrectiononUA-GEC
F0.5· uses extra data· 2024-03-08
74.09
SOTA
To Err Is Human, but Llamas Can Learn It Too arXiv:2403.05493