# Verifiable Claim Detection on DIALFACT (test)

Source: [Verifiable Claim Detection on DIALFACT (test)](<https://www.sota2.com/research/sota/verifiable-claim-detection-on-dialfact-test>)

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

Data updated: 2026-02-26T05:28:12.170Z

Evaluation of model performance on the test split of the DIALFACT dataset for Verifiable Claim Detection, reporting Accuracy, Verifiable F1, and Non-Verifiable 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 | Verifiable Claim Detection |
| Dataset (including any stated split) | DIALFACT (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/verifiable-claim-detection-on-dialfact-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Lexical+DNLI | 82.8 | Not recorded | 68fa6c0f1e209131cea31ce6 |
| DNLI | 82.1 | Not recorded | 68fa6c0f1e209131cea31ce6 |
| Lexical | 79.4 | Not recorded | 68fa6c0f1e209131cea31ce6 |
| Random | 50 | Not recorded | 68fa6c0f1e209131cea31ce6 |

### Lexical+DNLI

Accuracy: 82.8. Result ID: 698ec1ecffc3901de0a0d205.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

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

### DNLI

Accuracy: 82.1. Result ID: 698ec1ecffc3901de0a0d204.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa654f1e209131cea098dd.md>)

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

### Lexical

Accuracy: 79.4. Result ID: 698ec1ecffc3901de0a0d203.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

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

### Random

Accuracy: 50. Result ID: 698ec1ecffc3901de0a0d202.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.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.