# Error Detection on Relational-Tables

Source: [Error Detection on Relational-Tables](<https://www.sota2.com/research/sota/error-detection-on-relational-tables>)

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

Data updated: 2026-03-25T12:36:42.947Z

Evaluation of Error Detection performance on the Relational-Tables dataset, measured by F1 score.

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) | Relational-Tables |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/error-detection-on-relational-tables.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Table-Specialist | 52.9 | Not recorded | 68fa753f1e209131cea66c30 |
| GPT-4 | 46.5 | Not recorded | 68fa753f1e209131cea66c30 |
| Table-Specialist | 45.7 | Not recorded | 68fa753f1e209131cea66c30 |
| GPT-3.5 | 34 | Not recorded | 68fa753f1e209131cea66c30 |
| Table-Specialist | 16.1 | Not recorded | 68fa753f1e209131cea66c30 |
| Llama3.1-8B | 10.8 | Not recorded | 68fa753f1e209131cea66c30 |

### Table-Specialist

F1 Score: 52.9. Result ID: 69c3d6c147f34ce924ad0f74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4","Training Strategy":"Table-Specialist"}. This record does not assert independent reproduction.

### GPT-4

F1 Score: 46.5. Result ID: 69c3d6c147f34ce924ad0f73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4","Training Strategy":"Vanilla"}. This record does not assert independent reproduction.

### Table-Specialist

F1 Score: 45.7. Result ID: 69c3d6c147f34ce924ad0f72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

Recorded evaluation configuration: {"Base Model":"GPT-3.5","Training Strategy":"Table-Specialist"}. This record does not assert independent reproduction.

### GPT-3.5

F1 Score: 34. Result ID: 69c3d6c147f34ce924ad0f71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Base Model":"GPT-3.5","Training Strategy":"Vanilla"}. This record does not assert independent reproduction.

### Table-Specialist

F1 Score: 16.1. Result ID: 69c3d6c147f34ce924ad0f76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

Recorded evaluation configuration: {"Base Model":"Llama3.1-8B","Training Strategy":"Table-Specialist"}. This record does not assert independent reproduction.

### Llama3.1-8B

F1 Score: 10.8. Result ID: 69c3d6c147f34ce924ad0f75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eae1e209131cea41685.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Base Model":"Llama3.1-8B","Training Strategy":"Vanilla"}. This record does not assert independent reproduction.

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