# Short-video comment generation on Douyin dataset

Source: [Short-video comment generation on Douyin dataset](<https://www.sota2.com/research/sota/short-video-comment-generation-on-douyin-dataset>)

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

Data updated: 2026-04-14T07:27:15.203Z

Evaluation of models generating comments for short videos using the Douyin dataset, assessed via metrics focusing on Originality, Relevance, and Style Conformity.

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 | Short-video comment generation |
| Dataset (including any stated split) | Douyin dataset |
| Metric | Originality Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Originality Score](<https://www.sota2.com/research/sota/short-video-comment-generation-on-douyin-dataset.md?metric=Originality%20Score>): Higher is better; unit: SCALAR.

- [Relevance Score](<https://www.sota2.com/research/sota/short-video-comment-generation-on-douyin-dataset.md?metric=Relevance%20Score>): Higher is better; unit: SCALAR.

- [Style Conformity Score](<https://www.sota2.com/research/sota/short-video-comment-generation-on-douyin-dataset.md?metric=Style%20Conformity%20Score>): Higher is better; unit: SCALAR.

- [Total Score](<https://www.sota2.com/research/sota/short-video-comment-generation-on-douyin-dataset.md?metric=Total%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Originality Score | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3.5-9b | 1.75 | Not recorded | 69ddca067d0172140ec7995b |
| LOLGORITHM | 1.75 | Not recorded | 69ddca067d0172140ec7995b |
| V2Xum-LLM | 1.38 | Not recorded | 69ddca067d0172140ec7995b |
| LiveChat | 1.21 | Not recorded | 69ddca067d0172140ec7995b |

### Qwen3.5-9b

Originality Score: 1.75. Result ID: 69ddec3947f34ce924c4f90c.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca067d0172140ec7995b.md>)

Recorded evaluation configuration: {"inference\_strategy":"Direct"}. This record does not assert independent reproduction.

### LOLGORITHM

Originality Score: 1.75. Result ID: 69ddec3947f34ce924c4f90d.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca067d0172140ec7995b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca067d0172140ec7995b.md>)

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

### V2Xum-LLM

Originality Score: 1.38. Result ID: 69ddec3947f34ce924c4f90a.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca067d0172140ec7995b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c051e209131cea8beb2.md>)

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

### LiveChat

Originality Score: 1.21. Result ID: 69ddec3947f34ce924c4f90b.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca067d0172140ec7995b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb91e209131cea470ca.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.