Hurtful Sentence Completion On Honest En
평가 지표
HONEST
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | HONEST | Paper Title | Repository |
|---|---|---|---|
| BERT-large | 3.33 | HONEST: Measuring Hurtful Sentence Completion in Language Models | |
| RoBERTa-large | 2.62 | HONEST: Measuring Hurtful Sentence Completion in Language Models | |
| RoBERTa-base | 2.38 | HONEST: Measuring Hurtful Sentence Completion in Language Models | |
| BERT-base | 1.19 | HONEST: Measuring Hurtful Sentence Completion in Language Models | |
| DistilBERT-base | 1.90 | HONEST: Measuring Hurtful Sentence Completion in Language Models |
0 of 5 row(s) selected.