Legal-BERT

Reported on 6 benchmarks across 4 tasks · 2 papers

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

Natural Language Processing4 results

Natural Language UnderstandingonLexGLUE
CaseHOLD· 2021-10-03
75.1
best: 75.6 (CaseLaw-BERT)
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English arXiv:2110.00976
Question AnsweringonCaseHOLD
Macro F1 (10-fold)· 2021-04-18
68
best: 69.5 (Custom Legal-BERT)
When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset arXiv:2104.08671
Text ClassificationonTerms of Service
F1(10-fold)· 2021-04-18
75
best: 78.7 (Custom Legal-BERT)
When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset arXiv:2104.08671
Text ClassificationonOverruling
F1(10-fold)· 2021-04-18
96.3
best: 97.4 (Custom Legal-BERT)
When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset arXiv:2104.08671

Methodology2 results

ClassificationonTerms of Service
F1(10-fold)· 2021-04-18
75
best: 78.7 (Custom Legal-BERT)
When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset arXiv:2104.08671
ClassificationonOverruling
F1(10-fold)· 2021-04-18
96.3
best: 97.4 (Custom Legal-BERT)
When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset arXiv:2104.08671