# Toxicity Detection on BAD

Source: [Toxicity Detection on BAD](<https://www.sota2.com/research/sota/toxicity-detection-on-bad>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:43:11.251Z

Evaluation of model performance on the BAD dataset for the task of Toxicity Detection, typically reporting 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 | Toxicity Detection |
| Dataset (including any stated split) | BAD |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/toxicity-detection-on-bad.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| SOTA | 80.8 | Not recorded | 68fa6da71e209131cea3b2e5 |
| ContextSum | 76.5 | Not recorded | 68fa6da71e209131cea3b2e5 |
| ContextRNN | 76.3 | Not recorded | 68fa6da71e209131cea3b2e5 |
| ContextSingle | 75.2 | Not recorded | 68fa6da71e209131cea3b2e5 |
| TargetOnly | 74.8 | Not recorded | 68fa6da71e209131cea3b2e5 |
| NextSentPred | 74.7 | Not recorded | 68fa6da71e209131cea3b2e5 |
| TextConcat | 73.7 | Not recorded | 68fa6da71e209131cea3b2e5 |
| Perspective TargetOnly | 51.6 | Not recorded | 68fa6da71e209131cea3b2e5 |
| Azure TargetOnly | 49.2 | Not recorded | 68fa6da71e209131cea3b2e5 |
| Clarifai TargetOnly | 28.6 | Not recorded | 68fa6da71e209131cea3b2e5 |
| WW TargetOnly | 12.1 | Not recorded | 68fa6da71e209131cea3b2e5 |

### SOTA

F1 Score: 80.8. Result ID: 698fce193a6c314849fbfca5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ContextSum

F1 Score: 76.5. Result ID: 698fce193a6c314849fbfca2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Implementation](<https://github.com/MarvinChung/HW5-TextStyleTransfer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ContextRNN

F1 Score: 76.3. Result ID: 698fce193a6c314849fbfca3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Implementation](<https://github.com/MarvinChung/HW5-TextStyleTransfer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ContextSingle

F1 Score: 75.2. Result ID: 698fce193a6c314849fbfca1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Implementation](<https://github.com/MarvinChung/HW5-TextStyleTransfer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TargetOnly

F1 Score: 74.8. Result ID: 698fce193a6c314849fbfc9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NextSentPred

F1 Score: 74.7. Result ID: 698fce193a6c314849fbfca4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69a01e209131cea232ff.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TextConcat

F1 Score: 73.7. Result ID: 698fce193a6c314849fbfca0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Perspective TargetOnly

F1 Score: 51.6. Result ID: 698fce193a6c314849fbfc9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: {"Provider":"Perspective"}. This record does not assert independent reproduction.

### Azure TargetOnly

F1 Score: 49.2. Result ID: 698fce193a6c314849fbfc9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: {"Provider":"Azure"}. This record does not assert independent reproduction.

### Clarifai TargetOnly

F1 Score: 28.6. Result ID: 698fce193a6c314849fbfc9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: {"Provider":"Clarifai"}. This record does not assert independent reproduction.

### WW TargetOnly

F1 Score: 12.1. Result ID: 698fce193a6c314849fbfc9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da71e209131cea3b2e5.md>)

Recorded evaluation configuration: {"Provider":"WW"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.