# Cross-task generalization on Super-NaturalInstructions (one-shot)

Source: [Cross-task generalization on Super-NaturalInstructions (one-shot)](<https://www.sota2.com/research/sota/cross-task-generalization-on-super-naturalinstructions-one-shot>)

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

Data updated: 2026-02-26T06:00:41.982Z

Evaluation of cross-task generalization capabilities using the one-shot setting on the Super-NaturalInstructions dataset, typically measured using ROUGE metrics.

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 | Cross-task generalization |
| Dataset (including any stated split) | Super-NaturalInstructions one-shot |
| Metric | ROUGE-L |
| Unit | PERCENT |
| Direction | Higher 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

- [ROUGE-L](<https://www.sota2.com/research/sota/cross-task-generalization-on-super-naturalinstructions-one-shot.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ROUGE-L | Result date | Report paper |
| --- | --- | --- | --- |
| Random Exemplar | 39.59 | Not recorded | 68fa6fcd1e209131cea477f7 |
| Instruction Extractor | 37.85 | Not recorded | 68fa6fcd1e209131cea477f7 |
| Random Exemplar | 37.19 | Not recorded | 68fa6fcd1e209131cea477f7 |
| Instruction Extractor | 37.15 | Not recorded | 68fa6fcd1e209131cea477f7 |

### Random Exemplar

ROUGE-L: 39.59. Result ID: 6990fede3a6c31484904e1d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea477f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3bdf1.md>)

Recorded evaluation configuration: {"Training Instruction":"each task"}. This record does not assert independent reproduction.

### Instruction Extractor

ROUGE-L: 37.85. Result ID: 6990fede3a6c31484904e1da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea477f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea477f7.md>)

[Implementation](<https://github.com/misonuma/instopt>)

Recorded evaluation configuration: {"Optimization Protocol":"DP (direct parameterization)"}. This record does not assert independent reproduction.

### Random Exemplar

ROUGE-L: 37.19. Result ID: 6990fede3a6c31484904e1d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea477f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3bdf1.md>)

Recorded evaluation configuration: {"Training Instruction":"each instance"}. This record does not assert independent reproduction.

### Instruction Extractor

ROUGE-L: 37.15. Result ID: 6990fede3a6c31484904e1db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea477f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea477f7.md>)

[Implementation](<https://github.com/misonuma/instopt>)

Recorded evaluation configuration: {"Optimization Protocol":"IC (instance conversion)"}. This record does not assert independent reproduction.

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