# Information Extraction on Kleister Charity

Source: [Information Extraction on Kleister Charity](<https://www.sota2.com/research/sota/information-extraction-on-kleister-charity>)

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

Data updated: 2026-02-26T05:43:07.568Z

Evaluation of Information Extraction performance on the Kleister Charity dataset, typically measured using 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 | Information Extraction |
| Dataset (including any stated split) | Kleister Charity |
| 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/information-extraction-on-kleister-charity.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| LAMBERT | 81.34 | Not recorded | 68fa6af31e209131cea2b53e |
| LAMBERT | 79.94 | Not recorded | 68fa6af31e209131cea2b53e |
| RoBERTa | 77.88 | Not recorded | 68fa6af31e209131cea2b53e |
| LayoutLM | 77.2 | Not recorded | 68fa6af31e209131cea2b53e |
| LayoutLM | 77.13 | Not recorded | 68fa6af31e209131cea2b53e |
| RoBERTa | 76.36 | Not recorded | 68fa6af31e209131cea2b53e |

### LAMBERT

F1 Score: 81.34. Result ID: 698e4601ffc3901de09c391d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Implementation](<https://github.com/applicaai/lambert>)

Recorded evaluation configuration: {"Params":"125M","Training":"75M non-unique pages"}. This record does not assert independent reproduction.

### LAMBERT

F1 Score: 79.94. Result ID: 698e4601ffc3901de09c391c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Implementation](<https://github.com/applicaai/lambert>)

Recorded evaluation configuration: {"Params":"125M","Training":"16M non-unique pages"}. This record does not assert independent reproduction.

### RoBERTa

F1 Score: 77.88. Result ID: 698e4601ffc3901de09c3919.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Params":"125M","Training":"16M non-unique pages"}. This record does not assert independent reproduction.

### LayoutLM

F1 Score: 77.2. Result ID: 698e4601ffc3901de09c391a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67b41e209131cea17f0c.md>)

[Implementation](<https://aka.ms/layoutlm>)

Recorded evaluation configuration: {"Params":"113M"}. This record does not assert independent reproduction.

### LayoutLM

F1 Score: 77.13. Result ID: 698e4601ffc3901de09c391b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67b41e209131cea17f0c.md>)

[Implementation](<https://aka.ms/layoutlm>)

Recorded evaluation configuration: {"Params":"343M"}. This record does not assert independent reproduction.

### RoBERTa

F1 Score: 76.36. Result ID: 698e4601ffc3901de09c3918.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af31e209131cea2b53e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Params":"125M","Training":"original pretrained"}. This record does not assert independent reproduction.

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