# Response Reliability Estimation on ArabicaQA

Source: [Response Reliability Estimation on ArabicaQA](<https://www.sota2.com/research/sota/response-reliability-estimation-on-arabicaqa>)

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

Data updated: 2026-06-11T06:44:57.220Z

Evaluation of model response reliability estimation capabilities on the ArabicaQA dataset, measured using AUROC and PRR.

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 | Response reliability estimation |
| Dataset (including any stated split) | ArabicaQA |
| Metric | AUROC |
| Unit | SCALAR |
| 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

- [AUROC](<https://www.sota2.com/research/sota/response-reliability-estimation-on-arabicaqa.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [PRR](<https://www.sota2.com/research/sota/response-reliability-estimation-on-arabicaqa.md?metric=PRR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| GLU | 0.647 | Not recorded | 6a28f33c90966ade919c16f5 |
| RAUQ | 0.642 | Not recorded | 6a28f33c90966ade919c16f5 |
| RAUQ | 0.613 | Not recorded | 6a28f33c90966ade919c16f5 |
| RAUQ | 0.61 | Not recorded | 6a28f33c90966ade919c16f5 |
| GLU | 0.563 | Not recorded | 6a28f33c90966ade919c16f5 |
| GLU | 0.556 | Not recorded | 6a28f33c90966ade919c16f5 |
| LogTokU | 0.538 | Not recorded | 6a28f33c90966ade919c16f5 |
| LogTokU | 0.521 | Not recorded | 6a28f33c90966ade919c16f5 |
| LogTokU | 0.49 | Not recorded | 6a28f33c90966ade919c16f5 |

### GLU

AUROC: 0.647. Result ID: 6a2a5959fbc373592c26cc4b.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

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

### RAUQ

AUROC: 0.642. Result ID: 6a2a5959fbc373592c26cc4a.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

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

### RAUQ

AUROC: 0.613. Result ID: 6a2a5959fbc373592c26cc4d.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

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

### RAUQ

AUROC: 0.61. Result ID: 6a2a5959fbc373592c26cc47.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

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

### GLU

AUROC: 0.563. Result ID: 6a2a5959fbc373592c26cc4e.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

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

### GLU

AUROC: 0.556. Result ID: 6a2a5959fbc373592c26cc48.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

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

### LogTokU

AUROC: 0.538. Result ID: 6a2a5959fbc373592c26cc49.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa787f1e209131cea78b3c.md>)

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

### LogTokU

AUROC: 0.521. Result ID: 6a2a5959fbc373592c26cc46.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa787f1e209131cea78b3c.md>)

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

### LogTokU

AUROC: 0.49. Result ID: 6a2a5959fbc373592c26cc4c.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa787f1e209131cea78b3c.md>)

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

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