UnitedSynT5 (335M)

Reported on 3 benchmarks across 1 task · 1 paper

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

Natural Language Processing3 results

Natural Language Inferenceone-SNLI
Accuracy· uses extra data· 2024-12-12
89.8
best: 94 (UnitedSynT5 (3B))
First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI arXiv:2412.09263
Natural Language InferenceonSNLI
% Test Accuracy· uses extra data· 2024-12-12
93.5
best: 94.7 (UnitedSynT5 (3B))
First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI arXiv:2412.09263
Natural Language InferenceonMultiNLI
Matched· uses extra data· 2024-12-12
89.8
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI arXiv:2412.09263