# Sequence-level uncertainty estimation on SPANUQ-BENCH 2,000 sequences (test)

Source: [Sequence-level uncertainty estimation on SPANUQ-BENCH 2,000 sequences (test)](<https://www.sota2.com/research/sota/sequence-level-uncertainty-estimation-on-spanuq-bench-2-000-sequences-test>)

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

Data updated: 2026-07-08T07:01:22.345Z

Evaluation of sequence-level uncertainty estimation performance on the test split of the SPANUQ-BENCH dataset (2,000 sequences), utilizing correlation metrics (Spearman, Pearson), AUROC, and MAE.

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 | Sequence-level uncertainty estimation |
| Dataset (including any stated split) | SPANUQ-BENCH 2,000 sequences (test) |
| Metric | Spearman Correlation |
| 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

- [Spearman Correlation](<https://www.sota2.com/research/sota/sequence-level-uncertainty-estimation-on-spanuq-bench-2-000-sequences-test.md?metric=Spearman%20Correlation>): Higher is better; unit: SCALAR.

- [Pearson Correlation](<https://www.sota2.com/research/sota/sequence-level-uncertainty-estimation-on-spanuq-bench-2-000-sequences-test.md?metric=Pearson%20Correlation>): Higher is better; unit: SCALAR.

- [AUROC @ 0.3](<https://www.sota2.com/research/sota/sequence-level-uncertainty-estimation-on-spanuq-bench-2-000-sequences-test.md?metric=AUROC%20%40%200.3>): Higher is better; unit: PERCENT.

- [MAE](<https://www.sota2.com/research/sota/sequence-level-uncertainty-estimation-on-spanuq-bench-2-000-sequences-test.md?metric=MAE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Spearman Correlation | Result date | Report paper |
| --- | --- | --- | --- |
| MLP Probe | 0.858 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| SPANUQ | 0.851 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| SelfCheckGPT-NLI | 0.805 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| SE (10 samples) | 0.606 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| FActScore | 0.489 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| INSIDE (Jaccard) | 0.331 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| Verbalized Conf. | 0.322 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| KLE | 0.145 | Not recorded | 6a4dd9b34da6617fe9198c50 |
| P(True) | 0.14 | Not recorded | 6a4dd9b34da6617fe9198c50 |

### MLP Probe

Spearman Correlation: 0.858. Result ID: 6a4df5b760b88bb339d6afd7.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

Recorded evaluation configuration: {"Granularity":"Token","Oracle setting":"ground-truth span boundaries"}. This record does not assert independent reproduction.

### SPANUQ

Spearman Correlation: 0.851. Result ID: 6a4df5b760b88bb339d6afdf.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

Recorded evaluation configuration: {"Granularity":"Span"}. This record does not assert independent reproduction.

### SelfCheckGPT-NLI

Spearman Correlation: 0.805. Result ID: 6a4df5b760b88bb339d6afdd.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d943.md>)

Recorded evaluation configuration: {"Granularity":"Sequence"}. This record does not assert independent reproduction.

### SE (10 samples)

Spearman Correlation: 0.606. Result ID: 6a4df5b760b88bb339d6afda.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f141e209131cea43bf3.md>)

Recorded evaluation configuration: {"Granularity":"Sequence"}. This record does not assert independent reproduction.

### FActScore

Spearman Correlation: 0.489. Result ID: 6a4df5b760b88bb339d6afde.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d959.md>)

Recorded evaluation configuration: {"Granularity":"Claim"}. This record does not assert independent reproduction.

### INSIDE (Jaccard)

Spearman Correlation: 0.331. Result ID: 6a4df5b760b88bb339d6afdb.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75521e209131cea67225.md>)

Recorded evaluation configuration: {"Granularity":"Sequence"}. This record does not assert independent reproduction.

### Verbalized Conf.

Spearman Correlation: 0.322. Result ID: 6a4df5b760b88bb339d6afd8.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72941e209131cea573ff.md>)

Recorded evaluation configuration: {"Granularity":"Sequence"}. This record does not assert independent reproduction.

### KLE

Spearman Correlation: 0.145. Result ID: 6a4df5b760b88bb339d6afdc.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73601e209131cea5c05e.md>)

Recorded evaluation configuration: {"Granularity":"Sequence"}. This record does not assert independent reproduction.

### P(True)

Spearman Correlation: 0.14. Result ID: 6a4df5b760b88bb339d6afd9.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b34da6617fe9198c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Granularity":"Sequence"}. This record does not assert independent reproduction.

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