# Hate Speech Classification on MHS small models

Source: [Hate Speech Classification on MHS small models](<https://www.sota2.com/research/sota/hate-speech-classification-on-mhs-small-models>)

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

Data updated: 2026-05-27T09:52:18.377Z

Evaluation of Hate Speech Classification performance on the MHS small models dataset, measured using F1 score, Accuracy, Precision, and Recall.

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 classification |
| Dataset (including any stated split) | MHS small models |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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/hate-speech-classification-on-mhs-small-models.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/hate-speech-classification-on-mhs-small-models.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/hate-speech-classification-on-mhs-small-models.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/hate-speech-classification-on-mhs-small-models.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Attr. aware | 61.99 | Not recorded | 6a167acadbd7150506f801e1 |
| Persona | 60.42 | Not recorded | 6a167acadbd7150506f801e1 |
| Attr. value | 60.19 | Not recorded | 6a167acadbd7150506f801e1 |
| Definition | 59.86 | Not recorded | 6a167acadbd7150506f801e1 |
| Attr. aware | 58.53 | Not recorded | 6a167acadbd7150506f801e1 |
| Zero-shot | 58.08 | Not recorded | 6a167acadbd7150506f801e1 |
| Definition | 57.81 | Not recorded | 6a167acadbd7150506f801e1 |
| Vanilla | 56.34 | Not recorded | 6a167acadbd7150506f801e1 |
| Vanilla | 56.11 | Not recorded | 6a167acadbd7150506f801e1 |
| Persona | 54.57 | Not recorded | 6a167acadbd7150506f801e1 |
| Few-shot | 54.38 | Not recorded | 6a167acadbd7150506f801e1 |
| Few-shot | 50.19 | Not recorded | 6a167acadbd7150506f801e1 |
| Attr. value | 50.05 | Not recorded | 6a167acadbd7150506f801e1 |
| Zero-shot | 49.05 | Not recorded | 6a167acadbd7150506f801e1 |

### Attr. aware

F1 Score: 61.99. Result ID: 6a16bebffbc373592c105d37.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

### Persona

F1 Score: 60.42. Result ID: 6a16bebffbc373592c105d3a.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

### Attr. value

F1 Score: 60.19. Result ID: 6a16bebffbc373592c105d38.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

### Definition

F1 Score: 59.86. Result ID: 6a16bebffbc373592c105d36.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

### Attr. aware

F1 Score: 58.53. Result ID: 6a16bebffbc373592c105d3e.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Zero-shot

F1 Score: 58.08. Result ID: 6a16bebffbc373592c105d3b.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Definition

F1 Score: 57.81. Result ID: 6a16bebffbc373592c105d3d.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Vanilla

F1 Score: 56.34. Result ID: 6a16bebffbc373592c105d39.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

### Vanilla

F1 Score: 56.11. Result ID: 6a16bebffbc373592c105d40.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Persona

F1 Score: 54.57. Result ID: 6a16bebffbc373592c105d41.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Few-shot

F1 Score: 54.38. Result ID: 6a16bebffbc373592c105d3c.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Few-shot

F1 Score: 50.19. Result ID: 6a16bebffbc373592c105d35.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

### Attr. value

F1 Score: 50.05. Result ID: 6a16bebffbc373592c105d3f.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-7B"}. This record does not assert independent reproduction.

### Zero-shot

F1 Score: 49.05. Result ID: 6a16bebffbc373592c105d34.

[Reporting paper](<https://www.sota2.com/research/paper/6a167acadbd7150506f801e1.md>)

Recorded evaluation configuration: {"Backbone":"Llama-8B"}. This record does not assert independent reproduction.

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