# Suboptimal-claim detection on ClaimRev (test)

Source: [Suboptimal-claim detection on ClaimRev (test)](<https://www.sota2.com/research/sota/suboptimal-claim-detection-on-claimrev-test>)

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

Data updated: 2026-02-26T05:28:54.989Z

Evaluation of model performance on the test split of the ClaimRev dataset for Suboptimal-claim detection.

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 | Suboptimal-claim detection |
| Dataset (including any stated split) | ClaimRev (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/suboptimal-claim-detection-on-claimrev-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro F1 Score](<https://www.sota2.com/research/sota/suboptimal-claim-detection-on-claimrev-test.md?metric=Macro%20F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/suboptimal-claim-detection-on-claimrev-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/suboptimal-claim-detection-on-claimrev-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/suboptimal-claim-detection-on-claimrev-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FT-DeBERTa | 67.1 | Not recorded | 68fa6f801e209131cea46090 |
| FT-ELECTRA | 63.8 | Not recorded | 68fa6f801e209131cea46090 |
| ELECTRA + SVM | 63.2 | Not recorded | 68fa6f801e209131cea46090 |
| FT-BERT | 63.1 | Not recorded | 68fa6f801e209131cea46090 |
| BERT + SVM | 62.1 | Not recorded | 68fa6f801e209131cea46090 |
| DeBERTa + SVM | 61.5 | Not recorded | 68fa6f801e209131cea46090 |
| Flair + SVM | 60.1 | Not recorded | 68fa6f801e209131cea46090 |
| Glove + SVM | 54.9 | Not recorded | 68fa6f801e209131cea46090 |
| Random baseline | 50 | Not recorded | 68fa6f801e209131cea46090 |

### FT-DeBERTa

Accuracy: 67.1. Result ID: 6990c75c3a6c314849033b21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Implementation](<https://github.com/webis-de/ACL-23>)

Recorded evaluation configuration: {"Approach":"Fine-tuned"}. This record does not assert independent reproduction.

### FT-ELECTRA

Accuracy: 63.8. Result ID: 6990c75c3a6c314849033b20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Implementation](<https://github.com/webis-de/ACL-23>)

Recorded evaluation configuration: {"Approach":"Fine-tuned"}. This record does not assert independent reproduction.

### ELECTRA + SVM

Accuracy: 63.2. Result ID: 6990c75c3a6c314849033b1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673f1e209131cea15373.md>)

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

Recorded evaluation configuration: {"Approach":"Embed. + SVM","Embedding":"ELECTRA"}. This record does not assert independent reproduction.

### FT-BERT

Accuracy: 63.1. Result ID: 6990c75c3a6c314849033b1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Implementation](<https://github.com/webis-de/ACL-23>)

Recorded evaluation configuration: {"Approach":"Fine-tuned"}. This record does not assert independent reproduction.

### BERT + SVM

Accuracy: 62.1. Result ID: 6990c75c3a6c314849033b1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

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

Recorded evaluation configuration: {"Approach":"Embed. + SVM","Embedding":"BERT"}. This record does not assert independent reproduction.

### DeBERTa + SVM

Accuracy: 61.5. Result ID: 6990c75c3a6c314849033b1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aef1e209131cea2b2a6.md>)

[Implementation](<https://github.com/microsoft/DeBERTa111>)

Recorded evaluation configuration: {"Approach":"Embed. + SVM","Embedding":"DeBERTa"}. This record does not assert independent reproduction.

### Flair + SVM

Accuracy: 60.1. Result ID: 6990c75c3a6c314849033b1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

Recorded evaluation configuration: {"Approach":"Embed. + SVM","Embedding":"Flair"}. This record does not assert independent reproduction.

### Glove + SVM

Accuracy: 54.9. Result ID: 6990c75c3a6c314849033b1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.md>)

Recorded evaluation configuration: {"Approach":"Embed. + SVM","Embedding":"Glove"}. This record does not assert independent reproduction.

### Random baseline

Accuracy: 50. Result ID: 6990c75c3a6c314849033b22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46090.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.