# Dialogue Summarization on SAMSum

Source: [Dialogue Summarization on SAMSum](<https://www.sota2.com/research/sota/dialogue-summarization-on-samsum>)

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

Data updated: 2026-02-26T06:00:39.922Z

Evaluation of dialogue summarization performance on the SAMSum dataset, typically measured using ROUGE metrics (R-1, R-2, R-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 | Dialogue Summarization |
| Dataset (including any stated split) | SAMSum |
| Metric | ROUGE-2 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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-summarization-on-samsum.md?metric=ROUGE-2>): Higher is better; unit: PERCENT.

- [ROUGE-1](<https://www.sota2.com/research/sota/dialogue-summarization-on-samsum.md?metric=ROUGE-1>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | ROUGE-2 | Result date | Report paper |
| --- | --- | --- | --- |
| PEGASUS-2B (calibrated) | 29.88 | Not recorded | 68fa6d8f1e209131cea3a999 |
| ULL | 29.6 | Not recorded | 68fa6d8f1e209131cea3a999 |
| PEGASUS-2B (fine-tuned) | 29.21 | Not recorded | 68fa6d8f1e209131cea3a999 |
| BART-FT | 24.47 | Not recorded | 68fa6c141e209131cea31ff0 |
| Narrator | 13.23 | Not recorded | 68fa6c141e209131cea31ff0 |
| BART | 9.58 | Not recorded | 68fa6c141e209131cea31ff0 |
| BART-DIAL-DE | 9.52 | Not recorded | 68fa6c141e209131cea31ff0 |
| BART-CRD3-GEN | 9.09 | Not recorded | 68fa6c141e209131cea31ff0 |
| BART-CNN-GEN | 9.08 | Not recorded | 68fa6c141e209131cea31ff0 |
| GPT-2 | 0.74 | Not recorded | 68fa6c141e209131cea31ff0 |

### PEGASUS-2B (calibrated)

ROUGE-2: 29.88. Result ID: 698fba463a6c314849fb7267.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d8f1e209131cea3a999.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8f1e209131cea3a999.md>)

Recorded evaluation configuration: {"#params":"2B","beam size":10,"training":"SLiC"}. This record does not assert independent reproduction.

### ULL

ROUGE-2: 29.6. Result ID: 698fba463a6c314849fb7265.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d8f1e209131cea3a999.md>)

Recorded evaluation configuration: {"#params":"20B"}. This record does not assert independent reproduction.

### PEGASUS-2B (fine-tuned)

ROUGE-2: 29.21. Result ID: 698fba463a6c314849fb7266.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d8f1e209131cea3a999.md>)

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

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

Recorded evaluation configuration: {"#params":"2B","beam size":5}. This record does not assert independent reproduction.

### BART-FT

ROUGE-2: 24.47. Result ID: 698eca06ffc3901de0a1325d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

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

### Narrator

ROUGE-2: 13.23. Result ID: 698eca06ffc3901de0a13263.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

[Implementation](<https://github.com/zhaochaocs/Diana>)

Recorded evaluation configuration: {"pre-training\_data":"DIANA","pre-training\_task":"GEN","training\_mode":"zero-shot"}. This record does not assert independent reproduction.

### BART

ROUGE-2: 9.58. Result ID: 698eca06ffc3901de0a1325f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

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

Recorded evaluation configuration: {"training\_mode":"zero-shot"}. This record does not assert independent reproduction.

### BART-DIAL-DE

ROUGE-2: 9.52. Result ID: 698eca06ffc3901de0a13260.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

Recorded evaluation configuration: {"pre-training\_data":"DIAL","pre-training\_task":"DE","training\_mode":"zero-shot"}. This record does not assert independent reproduction.

### BART-CRD3-GEN

ROUGE-2: 9.09. Result ID: 698eca06ffc3901de0a13262.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

Recorded evaluation configuration: {"pre-training\_data":"CRD3","pre-training\_task":"GEN","training\_mode":"zero-shot"}. This record does not assert independent reproduction.

### BART-CNN-GEN

ROUGE-2: 9.08. Result ID: 698eca06ffc3901de0a13261.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.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: {"pre-training\_data":"CNN","pre-training\_task":"GEN","training\_mode":"zero-shot"}. This record does not assert independent reproduction.

### GPT-2

ROUGE-2: 0.74. Result ID: 698eca06ffc3901de0a1325e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31ff0.md>)

Recorded evaluation configuration: {"training\_mode":"zero-shot"}. This record does not assert independent reproduction.

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