ALUM (RoBERTa-LARGE)

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

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 InferenceonANLI test
A2· uses extra data· 2020-04-20
52.1
best: 72.5 (T5-3B (explanation prompting))
SOTA
Adversarial Training for Large Neural Language Models arXiv:2004.08994
Natural Language InferenceonANLI test
A1· uses extra data· 2020-04-20
72.3
best: 81.8 (T5-3B (explanation prompting))
Adversarial Training for Large Neural Language Models arXiv:2004.08994
Natural Language InferenceonANLI test
A3· uses extra data· 2020-04-20
48.4
best: 74.8 (T5-3B (explanation prompting))
Adversarial Training for Large Neural Language Models arXiv:2004.08994