# Extreme Summarization on XSum subset of 50 documents (test)

Source: [Extreme Summarization on XSum subset of 50 documents (test)](<https://www.sota2.com/research/sota/extreme-summarization-on-xsum-subset-of-50-documents-test>)

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

Data updated: 2026-02-26T06:03:42.497Z

Evaluation of Extreme Summarization performance on a specific 50-document test subset of the XSum dataset, measured using Score and QA 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 | Extreme Summarization |
| Dataset (including any stated split) | XSum subset of 50 documents (test) |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Score](<https://www.sota2.com/research/sota/extreme-summarization-on-xsum-subset-of-50-documents-test.md?metric=Score>): Higher is better; unit: SCALAR.

- [QA Score](<https://www.sota2.com/research/sota/extreme-summarization-on-xsum-subset-of-50-documents-test.md?metric=QA%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| GOLD | 0.431 | Not recorded | 68fa64bc1e209131cea06267 |
| T-CONVS2S | 0.037 | Not recorded | 68fa64bc1e209131cea06267 |
| EXT-ORACLE | -0.121 | Not recorded | 68fa64bc1e209131cea06267 |
| CONVS2S | -0.13 | Not recorded | 68fa64bc1e209131cea06267 |
| PTGEN | -0.218 | Not recorded | 68fa64bc1e209131cea06267 |

### GOLD

Score: 0.431. Result ID: 698c88b90b614d12cff14b78.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06267.md>)

Recorded evaluation configuration: {"Type":"Human-authored"}. This record does not assert independent reproduction.

### T-CONVS2S

Score: 0.037. Result ID: 698c88b90b614d12cff14b77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06267.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06267.md>)

[Implementation](<https://github.com/shashiongithub/XSum>)

Recorded evaluation configuration: {"Description":"Topic-Aware Convolutional Neural Networks"}. This record does not assert independent reproduction.

### EXT-ORACLE

Score: -0.121. Result ID: 698c88b90b614d12cff14b74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06267.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d71e209131ce9fb8c6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CONVS2S

Score: -0.13. Result ID: 698c88b90b614d12cff14b76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06267.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63811e209131ce9ff028.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PTGEN

Score: -0.218. Result ID: 698c88b90b614d12cff14b75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06267.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634a1e209131ce9fdbfb.md>)

[Implementation](<https://www.sota2.com/www.github.com/abisee/pointer-generator>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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