# Short-text Generation on Douban (test)

Source: [Short-text Generation on Douban (test)](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test>)

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

Data updated: 2026-02-26T05:43:30.932Z

Evaluation of short-text generation performance on the test split of the Douban dataset, utilizing metrics such as F1, ROUGE-L, BLEU scores, Distinctness, Perplexity (PPL), and Relevance.

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-text Generation |
| Dataset (including any stated split) | Douban (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

- [BLEU-2](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=BLEU-2>): Higher is better; unit: SCALAR.

- [BLEU-4](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=BLEU-4>): Higher is better; unit: SCALAR.

- [Distinct-2](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=Distinct-2>): Higher is better; unit: PERCENT.

- [PPL](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=PPL>): Lower is better; unit: SCALAR.

- [Relevance](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=Relevance>): Higher is better; unit: SCALAR.

- [Latency (s)](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

- [Memory (MB)](<https://www.sota2.com/research/sota/short-text-generation-on-douban-test.md?metric=Memory%20(MB)>): Lower is better; unit: SIZE.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| HOLO | 11.02 | Not recorded | 69802f5da8b01e76cc8e1475 |
| HOLO | 10.71 | Not recorded | 69802f5da8b01e76cc8e1475 |
| HOLO | 9.87 | Not recorded | 69802f5da8b01e76cc8e1475 |
| ChatGLM-6B | 9.69 | Not recorded | 69802f5da8b01e76cc8e1475 |
| EVA2.0-2.8B | 9.59 | Not recorded | 69802f5da8b01e76cc8e1475 |
| Belle-13B | 8.84 | Not recorded | 69802f5da8b01e76cc8e1475 |

### HOLO

F1 Score: 11.02. Result ID: 69965d895698665ec4a346e2.

[Reporting paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

Recorded evaluation configuration: {"Base Model":"Belle-13B"}. This record does not assert independent reproduction.

### HOLO

F1 Score: 10.71. Result ID: 69965d895698665ec4a346e0.

[Reporting paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

Recorded evaluation configuration: {"Base Model":"ChatGLM-6B"}. This record does not assert independent reproduction.

### HOLO

F1 Score: 9.87. Result ID: 69965d895698665ec4a346de.

[Reporting paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

Recorded evaluation configuration: {"Base Model":"EVA2.0-2.8B"}. This record does not assert independent reproduction.

### ChatGLM-6B

F1 Score: 9.69. Result ID: 69965d895698665ec4a346df.

[Reporting paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e374.md>)

[Implementation](<https://github.com/THUDM/GLM-130B/>)

Recorded evaluation configuration: {"Parameters":"6B"}. This record does not assert independent reproduction.

### EVA2.0-2.8B

F1 Score: 9.59. Result ID: 69965d895698665ec4a346dd.

[Reporting paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f41e209131cea4e5ca.md>)

Recorded evaluation configuration: {"Parameters":"2.8B"}. This record does not assert independent reproduction.

### Belle-13B

F1 Score: 8.84. Result ID: 69965d895698665ec4a346e1.

[Reporting paper](<https://www.sota2.com/research/paper/69802f5da8b01e76cc8e1475.md>)

Recorded evaluation configuration: {"Parameters":"13B"}. This record does not assert independent reproduction.

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