# Dialogue Style Transfer on Anime-style dialogue human evaluation set (test)

Source: [Dialogue Style Transfer on Anime-style dialogue human evaluation set (test)](<https://www.sota2.com/research/sota/dialogue-style-transfer-on-anime-style-dialogue-human-evaluation-set-test>)

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

Data updated: 2026-03-09T07:50:56.120Z

Human evaluation of dialogue style transfer performance on the test split of the Anime-style dialogue human evaluation set, measured across Semantic coherence, Style adherence, and Overall quality.

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 | Dialogue Style Transfer |
| Dataset (including any stated split) | Anime-style dialogue human evaluation set (test) |
| Metric | Semantic Coherence Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Semantic Coherence Score](<https://www.sota2.com/research/sota/dialogue-style-transfer-on-anime-style-dialogue-human-evaluation-set-test.md?metric=Semantic%20Coherence%20Score>): Higher is better; unit: SCALAR.

- [Style Adherence Score](<https://www.sota2.com/research/sota/dialogue-style-transfer-on-anime-style-dialogue-human-evaluation-set-test.md?metric=Style%20Adherence%20Score>): Higher is better; unit: SCALAR.

- [Overall Quality Score](<https://www.sota2.com/research/sota/dialogue-style-transfer-on-anime-style-dialogue-human-evaluation-set-test.md?metric=Overall%20Quality%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Semantic Coherence Score | Result date | Report paper |
| --- | --- | --- | --- |
| Model v2 | 4.24 | Not recorded | 69ae53d92d603e6de3e42817 |
| Baseline D | 4.03 | Not recorded | 69ae53d92d603e6de3e42817 |
| Baseline C | 3.47 | Not recorded | 69ae53d92d603e6de3e42817 |

### Model v2

Semantic Coherence Score: 4.24. Result ID: 69ae7bd06dbb7075b9565df8.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d92d603e6de3e42817.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53d92d603e6de3e42817.md>)

Recorded evaluation configuration: {"Inference protocol":"Inference-only"}. This record does not assert independent reproduction.

### Baseline D

Semantic Coherence Score: 4.03. Result ID: 69ae7bd06dbb7075b9565dfa.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d92d603e6de3e42817.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a891e209131cea83c41.md>)

Recorded evaluation configuration: {"Approach":"Prompt-based"}. This record does not assert independent reproduction.

### Baseline C

Semantic Coherence Score: 3.47. Result ID: 69ae7bd06dbb7075b9565df9.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53d92d603e6de3e42817.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Training":"Vanilla SFT"}. This record does not assert independent reproduction.

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