# Hate Speech Detection on Hate Speech Detection (test) Source: [Hate Speech Detection on Hate Speech Detection (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:23.713Z Evaluation of model performance on the test split of the dataset named 'Hate Speech Detection', measured using Macro-F1 score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Hate Speech Detection | | Dataset (including any stated split) | Hate Speech Detection (test) | | Metric | Macro F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Macro F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro F1 | Result date | Report paper | | --- | --- | --- | --- | | BERT-base + RL-MTL | 72.06 | Not recorded | 68fa6c1c1e209131cea3243e | | BERT-large + RL-MTL | 69.82 | Not recorded | 68fa6c1c1e209131cea3243e | | BERT-large + MTL | 69.78 | Not recorded | 68fa6c1c1e209131cea3243e | | BART-large + RL-MTL | 69.6 | Not recorded | 68fa6c1c1e209131cea3243e | | BERT-base + MTL | 69.21 | Not recorded | 68fa6c1c1e209131cea3243e | | BART-large | 68.91 | Not recorded | 68fa6c1c1e209131cea3243e | | BART-large + MTL | 67.79 | Not recorded | 68fa6c1c1e209131cea3243e | | BERT-large | 67.05 | Not recorded | 68fa6c1c1e209131cea3243e | | BERT-base | 66.47 | Not recorded | 68fa6c1c1e209131cea3243e | | XINet-large + RL-MTL | 61.97 | Not recorded | 68fa6c1c1e209131cea3243e | | XINet-large + MTL | 61.68 | Not recorded | 68fa6c1c1e209131cea3243e | | XINet-large | 59.14 | Not recorded | 68fa6c1c1e209131cea3243e | ### BERT-base + RL-MTL Macro F1: 72.06. Result ID: 698eda21ffc3901de0a23495. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-base","Framework":"RL-guided MTL"}. This record does not assert independent reproduction. ### BERT-large + RL-MTL Macro F1: 69.82. Result ID: 698eda21ffc3901de0a23496. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-large","Framework":"RL-guided MTL"}. This record does not assert independent reproduction. ### BERT-large + MTL Macro F1: 69.78. Result ID: 698eda21ffc3901de0a23492. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-large","Framework":"Multi-Task Learning"}. This record does not assert independent reproduction. ### BART-large + RL-MTL Macro F1: 69.6. Result ID: 698eda21ffc3901de0a23497. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART-large","Framework":"RL-guided MTL"}. This record does not assert independent reproduction. ### BERT-base + MTL Macro F1: 69.21. Result ID: 698eda21ffc3901de0a23491. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-base","Framework":"Multi-Task Learning"}. This record does not assert independent reproduction. ### BART-large Macro F1: 68.91. Result ID: 698eda21ffc3901de0a2348f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BART-large","Framework":"Base Model"}. This record does not assert independent reproduction. ### BART-large + MTL Macro F1: 67.79. Result ID: 698eda21ffc3901de0a23493. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART-large","Framework":"Multi-Task Learning"}. This record does not assert independent reproduction. ### BERT-large Macro F1: 67.05. Result ID: 698eda21ffc3901de0a2348e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-large","Framework":"Base Model"}. This record does not assert independent reproduction. ### BERT-base Macro F1: 66.47. Result ID: 698eda21ffc3901de0a2348d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-base","Framework":"Base Model"}. This record does not assert independent reproduction. ### XINet-large + RL-MTL Macro F1: 61.97. Result ID: 698eda21ffc3901de0a23498. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"XINet-large","Framework":"RL-guided MTL"}. This record does not assert independent reproduction. ### XINet-large + MTL Macro F1: 61.68. Result ID: 698eda21ffc3901de0a23494. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"XINet-large","Framework":"Multi-Task Learning"}. This record does not assert independent reproduction. ### XINet-large Macro F1: 59.14. Result ID: 698eda21ffc3901de0a23490. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"XINet-large","Framework":"Base Model"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.