# Toxicity Detection on CAD (Contextual Abuse Dataset) (val)

Source: [Toxicity Detection on CAD (Contextual Abuse Dataset) (val)](<https://www.sota2.com/research/sota/toxicity-detection-on-cad-contextual-abuse-dataset-val>)

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

Data updated: 2026-04-08T09:12:16.948Z

Evaluation of Toxicity Detection performance on the validation split of the Contextual Abuse Dataset (CAD), reporting 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 | Toxicity Detection |
| Dataset (including any stated split) | CAD (Contextual Abuse Dataset) (val) |
| Metric | Macro-F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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](<https://www.sota2.com/research/sota/toxicity-detection-on-cad-contextual-abuse-dataset-val.md?metric=Macro-F1>): Higher is better; unit: PERCENT.

- [Macro-F1 Delta](<https://www.sota2.com/research/sota/toxicity-detection-on-cad-contextual-abuse-dataset-val.md?metric=Macro-F1%20Delta>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Macro-F1 | Result date | Report paper |
| --- | --- | --- | --- |
| CoGate-LSTM | 73 | Not recorded | 68fa7c571e209131cea8da9a |
| BiLSTM + GloVe | 71 | Not recorded | 68fa7c571e209131cea8da9a |
| CoGate-LSTM | 71 | Not recorded | 68fa7c571e209131cea8da9a |
| BERT (fine-tuned) | 68 | Not recorded | 68fa7c571e209131cea8da9a |
| BiLSTM + GloVe | 68 | Not recorded | 68fa7c571e209131cea8da9a |
| BERT (fine-tuned) | 65 | Not recorded | 68fa7c571e209131cea8da9a |

### CoGate-LSTM

Macro-F1: 73. Result ID: 69d61bdf47f34ce924bee553.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Thr. adapt"}. This record does not assert independent reproduction.

### BiLSTM + GloVe

Macro-F1: 71. Result ID: 69d61bdf47f34ce924bee551.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Thr. adapt"}. This record does not assert independent reproduction.

### CoGate-LSTM

Macro-F1: 71. Result ID: 69d61bdf47f34ce924bee552.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### BERT (fine-tuned)

Macro-F1: 68. Result ID: 69d61bdf47f34ce924bee54f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Evaluation Protocol":"Thr. adapt"}. This record does not assert independent reproduction.

### BiLSTM + GloVe

Macro-F1: 68. Result ID: 69d61bdf47f34ce924bee550.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### BERT (fine-tuned)

Macro-F1: 65. Result ID: 69d61bdf47f34ce924bee54e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c571e209131cea8da9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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