# Dialogue Generation on Schema-Guided Dialog (test)

Source: [Dialogue Generation on Schema-Guided Dialog (test)](<https://www.sota2.com/research/sota/dialogue-generation-on-schema-guided-dialog-test>)

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

Data updated: 2026-02-26T06:00:39.965Z

Evaluation of dialogue response generation performance on the test split of the Schema-Guided Dialog dataset, measured using ROUGE-2 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 | Dialogue Generation |
| Dataset (including any stated split) | Schema-Guided Dialog (test) |
| Metric | ROUGE-2 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [ROUGE-2](<https://www.sota2.com/research/sota/dialogue-generation-on-schema-guided-dialog-test.md?metric=ROUGE-2>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ROUGE-2 | Result date | Report paper |
| --- | --- | --- | --- |
| UL20B | 44.1 | Not recorded | 68fa6eaf1e209131cea416bb |
| Gehrmann et al. | 36.8 | Not recorded | 68fa6eaf1e209131cea416bb |

### UL20B

ROUGE-2: 44.1. Result ID: 69903a933a6c314849ff1123.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416bb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416bb.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/ul2>)

Recorded evaluation configuration: {"mode":"supervised finetuning"}. This record does not assert independent reproduction.

### Gehrmann et al.

ROUGE-2: 36.8. Result ID: 69903a933a6c314849ff1122.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416bb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b11e209131cea23752.md>)

[Implementation](<https://gem-benchmark.com/>)

Recorded evaluation configuration: {"status":"previous state-of-the-art"}. This record does not assert independent reproduction.

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