TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Methodology/Classification/Civil Comments

Classification on Civil Comments

Metric: Recall (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Recall▼AugmentationsPaperDate↕Code
1XLNet0.9254NoA benchmark for toxic comment classification on ...2023-01-26Code
2XLM RoBERTa0.923NoA benchmark for toxic comment classification on ...2023-01-26Code
3BERTweet0.9216NoA benchmark for toxic comment classification on ...2023-01-26Code
4HateBERT0.9165NoA benchmark for toxic comment classification on ...2023-01-26Code
5AlBERT0.9104NoA benchmark for toxic comment classification on ...2023-01-26Code
6DistilBERT0.9001NoA benchmark for toxic comment classification on ...2023-01-26Code
7RoBERTa BCE0.8891NoA benchmark for toxic comment classification on ...2023-01-26Code
8RoBERTa Focal Loss0.8839NoA benchmark for toxic comment classification on ...2023-01-26Code
9Unfreeze Glove ResNet 560.8707NoA benchmark for toxic comment classification on ...2023-01-26Code
10Compact Convolutional Transformer (CCT)0.7983NoA benchmark for toxic comment classification on ...2023-01-26Code
11Unfreeze Glove ResNet 440.7759NoA benchmark for toxic comment classification on ...2023-01-26Code
12Freeze Glove ResNet 440.7053NoA benchmark for toxic comment classification on ...2023-01-26Code