RoBERTa-large+Self-Explaining

Reported on 3 benchmarks across 2 tasks · 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

Natural Language InferenceonSNLI
% Test Accuracy· 2020-12-03
92.3
best: 94.7 (UnitedSynT5 (3B))
SOTA
Self-Explaining Structures Improve NLP Models arXiv:2012.01786
Natural Language InferenceonSNLI
Parameters· 2020-12-03
340
best: 355 (Neural Tree Indexers for Text Understanding)
SOTA
Self-Explaining Structures Improve NLP Models arXiv:2012.01786
Sentiment AnalysisonSST-5 Fine-grained classification
Accuracy· 2020-12-03
59.1
best: 62.27 (Llama-3.3-70B + CAPO)
SOTA
Self-Explaining Structures Improve NLP Models arXiv:2012.01786