# Fabricated Table Detection on FABTAB GPT-4o In-Domain (test)

Source: [Fabricated Table Detection on FABTAB GPT-4o In-Domain (test)](<https://www.sota2.com/research/sota/fabricated-table-detection-on-fabtab-gpt-4o-in-domain-test>)

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

Data updated: 2026-03-23T10:54:14.368Z

Evaluation of model performance for detecting fabricated tables using the test split of the FABTAB GPT-4o In-Domain dataset, measured using AUROC, AUPRC, and specialized FPR/TPR thresholds.

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 | Fabricated Table Detection |
| Dataset (including any stated split) | FABTAB GPT-4o In-Domain (test) |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/fabricated-table-detection-on-fabtab-gpt-4o-in-domain-test.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [AUPRC](<https://www.sota2.com/research/sota/fabricated-table-detection-on-fabtab-gpt-4o-in-domain-test.md?metric=AUPRC>): Higher is better; unit: SCALAR.

- [TPR @ FPR=5%](<https://www.sota2.com/research/sota/fabricated-table-detection-on-fabtab-gpt-4o-in-domain-test.md?metric=TPR%20%40%20FPR%3D5%25>): Higher is better; unit: SCALAR.

- [FPR @ Operating Point 5%](<https://www.sota2.com/research/sota/fabricated-table-detection-on-fabtab-gpt-4o-in-domain-test.md?metric=FPR%20%40%20Operating%20Point%205%25>): Lower is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| FusedAll (RandomForest) | 0.987 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| FusedAll (LogReg) | 0.986 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| FusedAll (MLP) | 0.986 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| TAB-AUDIT (PPL4, LogReg) | 0.902 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| TAB-AUDIT (PPL4, LogReg) | 0.884 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| TAB-AUDIT (PPL4, LogReg) | 0.866 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| Binoculars (no training) | 0.683 | Not recorded | 69c0c8dc0636e5bf4afc3997 |
| DetectGPT-style (no training) | 0.397 | Not recorded | 69c0c8dc0636e5bf4afc3997 |

### FusedAll (RandomForest)

AUROC: 0.987. Result ID: 69c11af547f34ce924a95862.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

Recorded evaluation configuration: {"Observer":"GPT-2"}. This record does not assert independent reproduction.

### FusedAll (LogReg)

AUROC: 0.986. Result ID: 69c11af547f34ce924a95861.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

Recorded evaluation configuration: {"Observer":"GPT-2"}. This record does not assert independent reproduction.

### FusedAll (MLP)

AUROC: 0.986. Result ID: 69c11af547f34ce924a95863.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

Recorded evaluation configuration: {"Observer":"GPT-2"}. This record does not assert independent reproduction.

### TAB-AUDIT (PPL4, LogReg)

AUROC: 0.902. Result ID: 69c11af547f34ce924a9585f.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

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

### TAB-AUDIT (PPL4, LogReg)

AUROC: 0.884. Result ID: 69c11af547f34ce924a9585e.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

Recorded evaluation configuration: {"Observer":"GPT-2"}. This record does not assert independent reproduction.

### TAB-AUDIT (PPL4, LogReg)

AUROC: 0.866. Result ID: 69c11af547f34ce924a95860.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

Recorded evaluation configuration: {"Observer":"Llama"}. This record does not assert independent reproduction.

### Binoculars (no training)

AUROC: 0.683. Result ID: 69c11af547f34ce924a9585c.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75371e209131cea667f1.md>)

Recorded evaluation configuration: {"Observer":"shared"}. This record does not assert independent reproduction.

### DetectGPT-style (no training)

AUROC: 0.397. Result ID: 69c11af547f34ce924a9585d.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8dc0636e5bf4afc3997.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701a1e209131cea49064.md>)

Recorded evaluation configuration: {"Observer":"GPT-2"}. This record does not assert independent reproduction.

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