# Document Summarization on Social Media Document Summarization Human Evaluation Set (100 summaries)

Source: [Document Summarization on Social Media Document Summarization Human Evaluation Set (100 summaries)](<https://www.sota2.com/research/sota/document-summarization-on-social-media-document-summarization-human-evaluation-set-100-summaries>)

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

Data updated: 2026-02-26T05:45:22.893Z

Human evaluation of Document Summarization quality on the Social Media Document Summarization Human Evaluation Set (100 summaries), focusing on Fluency and Consistency 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 | Document Summarization |
| Dataset (including any stated split) | Social Media Document Summarization Human Evaluation Set (100 summaries) |
| Metric | Fluency (Mean 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

- [Fluency (Mean Score)](<https://www.sota2.com/research/sota/document-summarization-on-social-media-document-summarization-human-evaluation-set-100-summaries.md?metric=Fluency%20(Mean%20Score)>): Higher is better; unit: SCALAR.

- [Fluency (Variance)](<https://www.sota2.com/research/sota/document-summarization-on-social-media-document-summarization-human-evaluation-set-100-summaries.md?metric=Fluency%20(Variance)>): Lower is better; unit: SCALAR.

- [Consistency (Mean Score)](<https://www.sota2.com/research/sota/document-summarization-on-social-media-document-summarization-human-evaluation-set-100-summaries.md?metric=Consistency%20(Mean%20Score)>): Higher is better; unit: SCALAR.

- [Consistency (Variance)](<https://www.sota2.com/research/sota/document-summarization-on-social-media-document-summarization-human-evaluation-set-100-summaries.md?metric=Consistency%20(Variance)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Fluency (Mean Score) | Result date | Report paper |
| --- | --- | --- | --- |
| RASG | 2.65 | Not recorded | 68fa65351e209131cea08f6f |
| CGU | 2.2 | Not recorded | 68fa65351e209131cea08f6f |
| S2S | 2.17 | Not recorded | 68fa65351e209131cea08f6f |

### RASG

Fluency (Mean Score): 2.65. Result ID: 698ca2470b614d12cff217c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65351e209131cea08f6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65351e209131cea08f6f.md>)

[Implementation](<http://t.cn/EAH5JxS>)

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

### CGU

Fluency (Mean Score): 2.2. Result ID: 698ca2470b614d12cff217c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65351e209131cea08f6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64811e209131cea04f6b.md>)

[Implementation](<https://www.github.com/lancopku/Global-Encoding>)

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

### S2S

Fluency (Mean Score): 2.17. Result ID: 698ca2470b614d12cff217c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65351e209131cea08f6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa619e1e209131ce9f5369.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.
