# News Headline Generation on LaMP-4 1.0 (test)

Source: [News Headline Generation on LaMP-4 1.0 (test)](<https://www.sota2.com/research/sota/news-headline-generation-on-lamp-4-1-0-test>)

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

Data updated: 2026-02-26T06:00:35.494Z

Evaluation of News Headline Generation performance on the test split of the LaMP-4 1.0 dataset, assessed using ROUGE metrics (ROUGE-1 and ROUGE-L).

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 | News Headline Generation |
| Dataset (including any stated split) | LaMP-4 1.0 (test) |
| Metric | ROUGE-1 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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-1](<https://www.sota2.com/research/sota/news-headline-generation-on-lamp-4-1-0-test.md?metric=ROUGE-1>): Higher is better; unit: SCALAR.

- [ROUGE-L](<https://www.sota2.com/research/sota/news-headline-generation-on-lamp-4-1-0-test.md?metric=ROUGE-L>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ROUGE-1 | Result date | Report paper |
| --- | --- | --- | --- |
| In-Prompt Augmentation | 0.188 | Not recorded | 68fa73701e209131cea5c7af |
| In-Prompt Augmentation | 0.182 | Not recorded | 68fa73701e209131cea5c7af |
| FlanT5-XXL | 0.176 | Not recorded | 68fa73701e209131cea5c7af |
| FlanT5-XXL | 0.163 | Not recorded | 68fa73701e209131cea5c7af |
| In-Prompt Augmentation | 0.158 | Not recorded | 68fa73701e209131cea5c7af |
| In-Prompt Augmentation | 0.15 | Not recorded | 68fa73701e209131cea5c7af |
| GPT-3.5 | 0.146 | Not recorded | 68fa73701e209131cea5c7af |
| GPT-3.5 | 0.136 | Not recorded | 68fa73701e209131cea5c7af |

### In-Prompt Augmentation

ROUGE-1: 0.188. Result ID: 6992eb1d3a6c314849125a81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Implementation](<http://lamp-benchmark.github.io/>)

Recorded evaluation configuration: {"Backbone":"FlanT5-XXL","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### In-Prompt Augmentation

ROUGE-1: 0.182. Result ID: 6992eb1d3a6c314849125a7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Implementation](<http://lamp-benchmark.github.io/>)

Recorded evaluation configuration: {"Backbone":"FlanT5-XXL","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### FlanT5-XXL

ROUGE-1: 0.176. Result ID: 6992eb1d3a6c314849125a7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfa7.md>)

[Implementation](<https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints>)

Recorded evaluation configuration: {"Personalization":"None","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### FlanT5-XXL

ROUGE-1: 0.163. Result ID: 6992eb1d3a6c314849125a7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfa7.md>)

[Implementation](<https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints>)

Recorded evaluation configuration: {"Personalization":"None","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### In-Prompt Augmentation

ROUGE-1: 0.158. Result ID: 6992eb1d3a6c314849125a82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Implementation](<http://lamp-benchmark.github.io/>)

Recorded evaluation configuration: {"Backbone":"GPT-3.5","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### In-Prompt Augmentation

ROUGE-1: 0.15. Result ID: 6992eb1d3a6c314849125a7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

[Implementation](<http://lamp-benchmark.github.io/>)

Recorded evaluation configuration: {"Backbone":"GPT-3.5","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### GPT-3.5

ROUGE-1: 0.146. Result ID: 6992eb1d3a6c314849125a80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

Recorded evaluation configuration: {"Personalization":"None","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### GPT-3.5

ROUGE-1: 0.136. Result ID: 6992eb1d3a6c314849125a7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7af.md>)

Recorded evaluation configuration: {"Personalization":"None","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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