# Abstractive Summarization on CNNDM (test)

Source: [Abstractive Summarization on CNNDM (test)](<https://www.sota2.com/research/sota/abstractive-summarization-on-cnndm-test>)

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

Data updated: 2026-02-26T06:00:33.920Z

Evaluation of abstractive summarization performance on the test split of the CNN/DailyMail (CNNDM) dataset, measured using ROUGE metrics (ROUGE-1, ROUGE-2, 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 | Abstractive Summarization |
| Dataset (including any stated split) | CNNDM (test) |
| Metric | ROUGE-1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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/abstractive-summarization-on-cnndm-test.md?metric=ROUGE-1>): Higher is better; unit: PERCENT.

- [ROUGE-2](<https://www.sota2.com/research/sota/abstractive-summarization-on-cnndm-test.md?metric=ROUGE-2>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/abstractive-summarization-on-cnndm-test.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ROUGE-1 | Result date | Report paper |
| --- | --- | --- | --- |
| BRIO-Mul | 47.78 | Not recorded | 68fa6c2f1e209131cea32a8b |
| BRIO-Ctr | 47.28 | Not recorded | 68fa6c2f1e209131cea32a8b |
| SimCLS | 46.67 | Not recorded | 68fa6c2f1e209131cea32a8b |
| GSum | 45.94 | Not recorded | 68fa6c2f1e209131cea32a8b |
| GOLD-p | 45.4 | Not recorded | 68fa6c2f1e209131cea32a8b |
| SeqCo | 45.02 | Not recorded | 68fa6c2f1e209131cea32a8b |
| GOLD-s | 44.82 | Not recorded | 68fa6c2f1e209131cea32a8b |
| ConSum | 44.53 | Not recorded | 68fa6c2f1e209131cea32a8b |
| BART | 44.29 | Not recorded | 68fa6c2f1e209131cea32a8b |
| PEGASUS | 44.17 | Not recorded | 68fa6c2f1e209131cea32a8b |
| BART | 44.16 | Not recorded | 68fa6c2f1e209131cea32a8b |

### BRIO-Mul

ROUGE-1: 47.78. Result ID: 698eee2f3a6c314849f3a097.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Implementation](<https://github.com/yixinL7/BRIO>)

Recorded evaluation configuration: {"Backbone":"BART","Training Loss":"Multi-task Loss","Training Mode":"Fine-tuned"}. This record does not assert independent reproduction.

### BRIO-Ctr

ROUGE-1: 47.28. Result ID: 698eee2f3a6c314849f3a096.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Implementation](<https://github.com/yixinL7/BRIO>)

Recorded evaluation configuration: {"Backbone":"BART","Training Loss":"Contrastive Loss Only","Training Mode":"Fine-tuned"}. This record does not assert independent reproduction.

### SimCLS

ROUGE-1: 46.67. Result ID: 698eee2f3a6c314849f3a094.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0c1e209131cea25bc2.md>)

[Implementation](<https://github.com/yixinL7/SimCLS>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Model":"RoBERTa","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### GSum

ROUGE-1: 45.94. Result ID: 698eee2f3a6c314849f3a08f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ce1e209131cea2432f.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### GOLD-p

ROUGE-1: 45.4. Result ID: 698eee2f3a6c314849f3a092.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69751e209131cea2237f.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### SeqCo

ROUGE-1: 45.02. Result ID: 698eee2f3a6c314849f3a091.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4f1.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### GOLD-s

ROUGE-1: 44.82. Result ID: 698eee2f3a6c314849f3a093.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69751e209131cea2237f.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### ConSum

ROUGE-1: 44.53. Result ID: 698eee2f3a6c314849f3a090.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a961e209131cea2920c.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### BART

ROUGE-1: 44.29. Result ID: 698eee2f3a6c314849f3a095.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Current Paper Evaluation Script"}. This record does not assert independent reproduction.

### PEGASUS

ROUGE-1: 44.17. Result ID: 698eee2f3a6c314849f3a08e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f91e209131cea198c5.md>)

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

Recorded evaluation configuration: {"Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

### BART

ROUGE-1: 44.16. Result ID: 698eee2f3a6c314849f3a08d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"Backbone":"BART","Evaluation Source":"Original Paper"}. This record does not assert independent reproduction.

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