# Paraphrase Identification on PIT -\> WMT (test)

Source: [Paraphrase Identification on PIT -\> WMT (test)](<https://www.sota2.com/research/sota/paraphrase-identification-on-pit-wmt-test>)

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

Data updated: 2026-02-26T05:25:50.964Z

Evaluation of model performance on the WMT test split derived from the PIT dataset for paraphrase identification, measured using AUROC.

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 | Paraphrase Identification |
| Dataset (including any stated split) | PIT -\> WMT (test) |
| Metric | AUROC |
| Unit | SCALAR |
| 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

- [AUROC](<https://www.sota2.com/research/sota/paraphrase-identification-on-pit-wmt-test.md?metric=AUROC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| OODP | 0.85 | Not recorded | 68fa6d931e209131cea3ac4f |
| GAP | 0.847 | Not recorded | 68fa6d931e209131cea3ac4f |
| GAPX | 0.811 | Not recorded | 68fa6d931e209131cea3ac4f |
| RoBERTa | 0.769 | Not recorded | 68fa6d931e209131cea3ac4f |
| BART | 0.764 | Not recorded | 68fa6d931e209131cea3ac4f |
| BERT+EP | 0.746 | Not recorded | 68fa6d931e209131cea3ac4f |
| BERT | 0.707 | Not recorded | 68fa6d931e209131cea3ac4f |
| IDP | 0.657 | Not recorded | 68fa6d931e209131cea3ac4f |
| BOW | 0.525 | Not recorded | 68fa6d931e209131cea3ac4f |
| BILSTM | 0.515 | Not recorded | 68fa6d931e209131cea3ac4f |

### OODP

AUROC: 0.85. Result ID: 698faba13a6c314849faf71c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Implementation](<https://github.com/YifeiZhou02/generalized_paraphrase_identification>)

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

### GAP

AUROC: 0.847. Result ID: 698faba13a6c314849faf71d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Implementation](<https://github.com/YifeiZhou02/generalized_paraphrase_identification>)

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

### GAPX

AUROC: 0.811. Result ID: 698faba13a6c314849faf71e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Implementation](<https://github.com/YifeiZhou02/generalized_paraphrase_identification>)

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

### RoBERTa

AUROC: 0.769. Result ID: 698faba13a6c314849faf71a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

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

### BART

AUROC: 0.764. Result ID: 698faba13a6c314849faf719.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

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

### BERT+EP

AUROC: 0.746. Result ID: 698faba13a6c314849faf718.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

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

### BERT

AUROC: 0.707. Result ID: 698faba13a6c314849faf717.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

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

### IDP

AUROC: 0.657. Result ID: 698faba13a6c314849faf71b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

[Implementation](<https://github.com/YifeiZhou02/generalized_paraphrase_identification>)

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

### BOW

AUROC: 0.525. Result ID: 698faba13a6c314849faf715.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

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

### BILSTM

AUROC: 0.515. Result ID: 698faba13a6c314849faf716.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac4f.md>)

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.