# Error Detection on TruthfulQA (full)

Source: [Error Detection on TruthfulQA (full)](<https://www.sota2.com/research/sota/error-detection-on-truthfulqa-full>)

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

Data updated: 2026-03-26T14:25:31.516Z

Evaluation of model performance on the full version of the TruthfulQA dataset, focusing on error detection capabilities, measured using metrics such as 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 | Error Detection |
| Dataset (including any stated split) | TruthfulQA (full) |
| Metric | AUROC |
| Unit | SCALAR |
| 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

- [AUROC](<https://www.sota2.com/research/sota/error-detection-on-truthfulqa-full.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [95% CI (AUROC)](<https://www.sota2.com/research/sota/error-detection-on-truthfulqa-full.md?metric=95%25%20CI%20(AUROC)>): Higher is better; unit: SCALAR.

- [Cost Multiplier](<https://www.sota2.com/research/sota/error-detection-on-truthfulqa-full.md?metric=Cost%20Multiplier>): Lower is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| B1 mean entropy | 0.599 | Not recorded | 69c4bdb60636e5bf4afc7760 |
| SelfCheck-Emb | 0.588 | Not recorded | 69c4bdb60636e5bf4afc7760 |
| SE-Jaccard | 0.548 | Not recorded | 69c4bdb60636e5bf4afc7760 |
| SE-Embedding | 0.542 | Not recorded | 69c4bdb60636e5bf4afc7760 |

### B1 mean entropy

AUROC: 0.599. Result ID: 69c541bf47f34ce924af22f7.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb60636e5bf4afc7760.md>)

Recorded evaluation configuration: {"description":"Baseline first-beam entropy"}. This record does not assert independent reproduction.

### SelfCheck-Emb

AUROC: 0.588. Result ID: 69c541bf47f34ce924af22f8.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb60636e5bf4afc7760.md>)

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

Recorded evaluation configuration: {"Sample size (k)":"5"}. This record does not assert independent reproduction.

### SE-Jaccard

AUROC: 0.548. Result ID: 69c541bf47f34ce924af22f9.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb60636e5bf4afc7760.md>)

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

Recorded evaluation configuration: {"Sample size (N)":"10"}. This record does not assert independent reproduction.

### SE-Embedding

AUROC: 0.542. Result ID: 69c541bf47f34ce924af22fa.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb60636e5bf4afc7760.md>)

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

Recorded evaluation configuration: {"Sample size (N)":"10"}. This record does not assert independent reproduction.

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