# Short-text Generation on Weibo

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

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

Data updated: 2026-02-26T05:47:12.828Z

Evaluation of short-text generation capabilities on the Weibo dataset, typically assessed using human-centric metrics like Informativeness, Coherence, and Humanness.

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) | Weibo |
| Metric | Informativeness |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

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

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

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

## Recorded results

| Method | Informativeness | Result date | Report paper |
| --- | --- | --- | --- |
| ChatGLM-6B | 3.39 | Not recorded | 69802f5da8b01e76cc8e1475 |
| Belle-13B | 3.21 | Not recorded | 69802f5da8b01e76cc8e1475 |
| HOLOChatGLM−6B | 3.2 | Not recorded | 69802f5da8b01e76cc8e1475 |
| HOLOBelle−13B | 3.07 | Not recorded | 69802f5da8b01e76cc8e1475 |
| HOLOEVA2.0−2.8B | 3.06 | Not recorded | 69802f5da8b01e76cc8e1475 |
| EVA2.0-2.8B | 2.75 | Not recorded | 69802f5da8b01e76cc8e1475 |

### ChatGLM-6B

Informativeness: 3.39. Result ID: 69965d895698665ec4a346d3.

[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: {"Parameter scale":"6B"}. This record does not assert independent reproduction.

### Belle-13B

Informativeness: 3.21. Result ID: 69965d895698665ec4a346d5.

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

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

### HOLOChatGLM−6B

Informativeness: 3.2. Result ID: 69965d895698665ec4a346d4.

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

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

Recorded evaluation configuration: {"Backbone":"ChatGLM-6B","Parameter scale":"6B"}. This record does not assert independent reproduction.

### HOLOBelle−13B

Informativeness: 3.07. Result ID: 69965d895698665ec4a346d6.

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

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

Recorded evaluation configuration: {"Backbone":"Belle-13B","Parameter scale":"13B"}. This record does not assert independent reproduction.

### HOLOEVA2.0−2.8B

Informativeness: 3.06. Result ID: 69965d895698665ec4a346d2.

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

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

Recorded evaluation configuration: {"Backbone":"EVA2.0-2.8B","Parameter scale":"2.8B"}. This record does not assert independent reproduction.

### EVA2.0-2.8B

Informativeness: 2.75. Result ID: 69965d895698665ec4a346d1.

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

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

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

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