# Hallucination Detection on SC-GPT4

Source: [Hallucination Detection on SC-GPT4](<https://www.sota2.com/research/sota/hallucination-detection-on-sc-gpt4>)

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

Data updated: 2026-04-08T06:36:52.669Z

Evaluation of model performance on hallucination detection using the SC-GPT4 dataset, typically measured using 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 | Hallucination Detection |
| Dataset (including any stated split) | SC-GPT4 |
| Metric | AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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/hallucination-detection-on-sc-gpt4.md?metric=AUROC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| SELFCHECKGPT+f | 76.4 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SELFCHECKGPT | 76 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SC+f | 73.3 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SELFCHECKGPT+f | 72.5 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SELFCHECKGPT | 71.9 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SELFCHECKGPT+f | 70.3 | Not recorded | 68fa7a4a1e209131cea823a4 |
| DIRECT+f | 69.1 | Not recorded | 68fa7a4a1e209131cea823a4 |
| DIRECT+f | 68 | Not recorded | 68fa7a4a1e209131cea823a4 |
| DIRECT | 67.9 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SELFCHECKGPT | 67.8 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SC | 65.8 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SC+f | 65.3 | Not recorded | 68fa7a4a1e209131cea823a4 |
| DIRECT | 63.8 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SC | 62.3 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SC+f | 60.5 | Not recorded | 68fa7a4a1e209131cea823a4 |
| DIRECT+f | 58 | Not recorded | 68fa7a4a1e209131cea823a4 |
| DIRECT | 53.4 | Not recorded | 68fa7a4a1e209131cea823a4 |
| SC | 50.6 | Not recorded | 68fa7a4a1e209131cea823a4 |

### SELFCHECKGPT+f

AUROC: 76.4. Result ID: 69d5f6e047f34ce924bdf7b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"LLaMA 3.1","Future Context":"true"}. This record does not assert independent reproduction.

### SELFCHECKGPT

AUROC: 76. Result ID: 69d5f6e047f34ce924bdf7b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"LLaMA 3.1","Future Context":"false"}. This record does not assert independent reproduction.

### SC+f

AUROC: 73.3. Result ID: 69d5f6e047f34ce924bdf7bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"LLaMA 3.1","Future Context":"true"}. This record does not assert independent reproduction.

### SELFCHECKGPT+f

AUROC: 72.5. Result ID: 69d5f6e047f34ce924bdf7bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Gemma 3","Future Context":"true"}. This record does not assert independent reproduction.

### SELFCHECKGPT

AUROC: 71.9. Result ID: 69d5f6e047f34ce924bdf7be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Gemma 3","Future Context":"false"}. This record does not assert independent reproduction.

### SELFCHECKGPT+f

AUROC: 70.3. Result ID: 69d5f6e047f34ce924bdf7c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Qwen 2.5","Future Context":"true"}. This record does not assert independent reproduction.

### DIRECT+f

AUROC: 69.1. Result ID: 69d5f6e047f34ce924bdf7c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Qwen 2.5","Future Context":"true"}. This record does not assert independent reproduction.

### DIRECT+f

AUROC: 68. Result ID: 69d5f6e047f34ce924bdf7b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"LLaMA 3.1","Future Context":"true"}. This record does not assert independent reproduction.

### DIRECT

AUROC: 67.9. Result ID: 69d5f6e047f34ce924bdf7c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Qwen 2.5","Future Context":"false"}. This record does not assert independent reproduction.

### SELFCHECKGPT

AUROC: 67.8. Result ID: 69d5f6e047f34ce924bdf7c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Qwen 2.5","Future Context":"false"}. This record does not assert independent reproduction.

### SC

AUROC: 65.8. Result ID: 69d5f6e047f34ce924bdf7ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"LLaMA 3.1","Future Context":"false"}. This record does not assert independent reproduction.

### SC+f

AUROC: 65.3. Result ID: 69d5f6e047f34ce924bdf7c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Gemma 3","Future Context":"true"}. This record does not assert independent reproduction.

### DIRECT

AUROC: 63.8. Result ID: 69d5f6e047f34ce924bdf7b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"LLaMA 3.1","Future Context":"false"}. This record does not assert independent reproduction.

### SC

AUROC: 62.3. Result ID: 69d5f6e047f34ce924bdf7c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Gemma 3","Future Context":"false"}. This record does not assert independent reproduction.

### SC+f

AUROC: 60.5. Result ID: 69d5f6e047f34ce924bdf7c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Qwen 2.5","Future Context":"true"}. This record does not assert independent reproduction.

### DIRECT+f

AUROC: 58. Result ID: 69d5f6e047f34ce924bdf7bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Gemma 3","Future Context":"true"}. This record does not assert independent reproduction.

### DIRECT

AUROC: 53.4. Result ID: 69d5f6e047f34ce924bdf7bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Gemma 3","Future Context":"false"}. This record does not assert independent reproduction.

### SC

AUROC: 50.6. Result ID: 69d5f6e047f34ce924bdf7c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a4.md>)

Recorded evaluation configuration: {"Detector":"Qwen 2.5","Future Context":"false"}. This record does not assert independent reproduction.

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