# Fact-based Text Editing on ROTOEDIT (test)

Source: [Fact-based Text Editing on ROTOEDIT (test)](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test>)

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

Data updated: 2026-02-26T05:36:48.887Z

Evaluation of Fact-based Text Editing performance on the test split of the ROTOEDIT dataset, assessed using metrics like BLEU, SARI, KEEP, ADD, DELETE, EM, Precision, Recall, and F1.

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 | Fact-based Text Editing |
| Dataset (including any stated split) | ROTOEDIT (test) |
| Metric | BLEU |
| Unit | PERCENT |
| 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

- [BLEU](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=BLEU>): Higher is better; unit: PERCENT.

- [SARI](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=SARI>): Higher is better; unit: PERCENT.

- [KEEP](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=KEEP>): Higher is better; unit: PERCENT.

- [ADD](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=ADD>): Higher is better; unit: SCALAR.

- [DELETE](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=DELETE>): Lower is better; unit: PERCENT.

- [EM](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=EM>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/fact-based-text-editing-on-rotoedit-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU | Result date | Report paper |
| --- | --- | --- | --- |
| FACTEDITOR | 84.43 | Not recorded | 68fa69b21e209131cea23826 |
| ENCDECEDITOR | 83.36 | Not recorded | 68fa69b21e209131cea23826 |
| Text-to-Text | 78.07 | Not recorded | 68fa69b21e209131cea23826 |
| No-Editing | 74.95 | Not recorded | 68fa69b21e209131cea23826 |
| Table-to-Text | 24.87 | Not recorded | 68fa69b21e209131cea23826 |

### FACTEDITOR

BLEU: 84.43. Result ID: 698dd71bffc3901de09900a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826.md>)

[Implementation](<https://github.com/isomap/factedit>)

Recorded evaluation configuration: {"Model Category":"Fact-based text editing"}. This record does not assert independent reproduction.

### ENCDECEDITOR

BLEU: 83.36. Result ID: 698dd71bffc3901de09900a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826.md>)

Recorded evaluation configuration: {"Model Category":"Fact-based text editing"}. This record does not assert independent reproduction.

### Text-to-Text

BLEU: 78.07. Result ID: 698dd71bffc3901de09900a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826.md>)

Recorded evaluation configuration: {"Model Category":"Baselines"}. This record does not assert independent reproduction.

### No-Editing

BLEU: 74.95. Result ID: 698dd71bffc3901de09900a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826.md>)

Recorded evaluation configuration: {"Model Category":"Baselines"}. This record does not assert independent reproduction.

### Table-to-Text

BLEU: 24.87. Result ID: 698dd71bffc3901de09900a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23826.md>)

Recorded evaluation configuration: {"Model Category":"Baselines"}. This record does not assert independent reproduction.

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