# Social Norm Dialogue Generation on Prosocial-Dialog Korean

Source: [Social Norm Dialogue Generation on Prosocial-Dialog Korean](<https://www.sota2.com/research/sota/social-norm-dialogue-generation-on-prosocial-dialog-korean>)

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

Data updated: 2026-03-13T07:08:02.342Z

Evaluation of model performance on generating dialogues adhering to social norms using the Prosocial-Dialog Korean dataset, typically measured via human preference scores.

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 | Social Norm Dialogue Generation |
| Dataset (including any stated split) | Prosocial-Dialog Korean |
| Metric | Human Preference |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Human Preference](<https://www.sota2.com/research/sota/social-norm-dialogue-generation-on-prosocial-dialog-korean.md?metric=Human%20Preference>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Human Preference | Result date | Report paper |
| --- | --- | --- | --- |
| V2R | 68 | Not recorded | 68fa7b7f1e209131cea88b10 |
| Untuned GPT-4o-mini | 32 | Not recorded | 68fa7b7f1e209131cea88b10 |

### V2R

Human Preference: 68. Result ID: 69b3b5f847f34ce9249d2d54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b7f1e209131cea88b10.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b7f1e209131cea88b10.md>)

Recorded evaluation configuration: {"Evaluation condition":"Blind","Annotators":"Native speakers","Base model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### Untuned GPT-4o-mini

Human Preference: 32. Result ID: 69b3b5f847f34ce9249d2d55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b7f1e209131cea88b10.md>)

Recorded evaluation configuration: {"Evaluation condition":"Blind","Annotators":"Native speakers"}. This record does not assert independent reproduction.

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