# Short-continuation text generation on Multi-domain short-continuation

Source: [Short-continuation text generation on Multi-domain short-continuation](<https://www.sota2.com/research/sota/short-continuation-text-generation-on-multi-domain-short-continuation>)

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

Data updated: 2026-07-07T10:22:06.298Z

Evaluation of short-continuation text generation performance on the Multi-domain short-continuation dataset, measured using MMD^2, Energy, and PPL.

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-continuation text generation |
| Dataset (including any stated split) | Multi-domain short-continuation |
| Metric | MMD^2 |
| Unit | SCALAR |
| Direction | Lower 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

- [MMD^2](<https://www.sota2.com/research/sota/short-continuation-text-generation-on-multi-domain-short-continuation.md?metric=MMD%5E2>): Lower is better; unit: SCALAR.

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

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

## Recorded results

| Method | MMD^2 | Result date | Report paper |
| --- | --- | --- | --- |
| MoEMA | 0.402 | Not recorded | 6a4c882e85dba69fef8b2b7d |
| StaticMA | 0.412 | Not recorded | 6a4c882e85dba69fef8b2b7d |
| SimpleAvg | 0.413 | Not recorded | 6a4c882e85dba69fef8b2b7d |
| BestSingle | 0.432 | Not recorded | 6a4c882e85dba69fef8b2b7d |

### MoEMA

MMD^2: 0.402. Result ID: 6a4cd33a60b88bb339ca7842.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: {"Evaluation feature space":"GPT-2","Evaluation protocol":"Averages over five random repeats","Weight type":"input-adaptive"}. This record does not assert independent reproduction.

### StaticMA

MMD^2: 0.412. Result ID: 6a4cd33a60b88bb339ca7841.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: {"Evaluation feature space":"GPT-2","Evaluation protocol":"Averages over five random repeats","Weight type":"fixed-weight"}. This record does not assert independent reproduction.

### SimpleAvg

MMD^2: 0.413. Result ID: 6a4cd33a60b88bb339ca7840.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: {"Evaluation feature space":"GPT-2","Evaluation protocol":"Averages over five random repeats"}. This record does not assert independent reproduction.

### BestSingle

MMD^2: 0.432. Result ID: 6a4cd33a60b88bb339ca783f.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: {"Evaluation feature space":"GPT-2","Evaluation protocol":"Averages over five random repeats"}. This record does not assert independent reproduction.

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