# Style Representation Evaluation on STEL-or-Content Cross-lingual (averaged across languages)

Source: [Style Representation Evaluation on STEL-or-Content Cross-lingual (averaged across languages)](<https://www.sota2.com/research/sota/style-representation-evaluation-on-stel-or-content-cross-lingual-averaged-across-languages>)

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

Data updated: 2026-02-26T05:45:30.495Z

Evaluation of Style Representation capabilities on the STEL-or-Content Cross-lingual dataset, averaged across multiple languages, focusing on metrics like Formality.

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 | Style Representation Evaluation |
| Dataset (including any stated split) | STEL-or-Content Cross-lingual (averaged across languages) |
| Metric | Formality |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Formality](<https://www.sota2.com/research/sota/style-representation-evaluation-on-stel-or-content-cross-lingual-averaged-across-languages.md?metric=Formality>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Formality | Result date | Report paper |
| --- | --- | --- | --- |
| MSTYLEDISTANCE | 0.53 | Not recorded | 68fa770c1e209131cea70be3 |
| STYLEDISTANCE | 0.49 | Not recorded | 68fa770c1e209131cea70be3 |
| Wegmann et al. (2022) | 0.45 | Not recorded | 68fa770c1e209131cea70be3 |
| LISA | 0.27 | Not recorded | 68fa770c1e209131cea70be3 |
| xlm-roberta-base | 0.19 | Not recorded | 68fa770c1e209131cea70be3 |

### MSTYLEDISTANCE

Formality: 0.53. Result ID: 699455a73a6c3148491c9445.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770c1e209131cea70be3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770c1e209131cea70be3.md>)

[Implementation](<https://huggingface.co/StyleDistance/mstyledistance>)

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

### STYLEDISTANCE

Formality: 0.49. Result ID: 699455a73a6c3148491c9442.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770c1e209131cea70be3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8b2.md>)

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

### Wegmann et al. (2022)

Formality: 0.45. Result ID: 699455a73a6c3148491c9441.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770c1e209131cea70be3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c441e209131cea331f0.md>)

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

### LISA

Formality: 0.27. Result ID: 699455a73a6c3148491c9444.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770c1e209131cea70be3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d39d.md>)

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

### xlm-roberta-base

Formality: 0.19. Result ID: 699455a73a6c3148491c9443.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770c1e209131cea70be3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67521e209131cea15706.md>)

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

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