# Document-level Relation Extraction on Re-DocRED Full Dataset 1.0 (test)

Source: [Document-level Relation Extraction on Re-DocRED Full Dataset 1.0 (test)](<https://www.sota2.com/research/sota/document-level-relation-extraction-on-re-docred-full-dataset-1-0-test>)

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

Data updated: 2026-02-26T05:58:33.125Z

Evaluation of model performance on Document-level Relation Extraction using the test split of the Re-DocRED Full Dataset 1.0, reporting Precision, Recall, and F1 scores.

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 | Document-level Relation Extraction |
| Dataset (including any stated split) | Re-DocRED Full Dataset 1.0 (test) |
| Metric | Precision |
| 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

- [Precision](<https://www.sota2.com/research/sota/document-level-relation-extraction-on-re-docred-full-dataset-1-0-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Precision (Ignored)](<https://www.sota2.com/research/sota/document-level-relation-extraction-on-re-docred-full-dataset-1-0-test.md?metric=Precision%20(Ignored)>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/document-level-relation-extraction-on-re-docred-full-dataset-1-0-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/document-level-relation-extraction-on-re-docred-full-dataset-1-0-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [F1 Score (Ignored)](<https://www.sota2.com/research/sota/document-level-relation-extraction-on-re-docred-full-dataset-1-0-test.md?metric=F1%20Score%20(Ignored)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| DREEAM-DOREMI | 79.39 | Not recorded | 696dba60e25ad2fa9d1ecb1b |
| DREEAM-DOREMI | 77.01 | Not recorded | 696dba60e25ad2fa9d1ecb1b |
| ATLOP-DOREMI | 74.86 | Not recorded | 696dba60e25ad2fa9d1ecb1b |
| ATLOP-DOREMI | 74.8 | Not recorded | 696dba60e25ad2fa9d1ecb1b |
| GPT-4.1 | 16.12 | Not recorded | 696dba60e25ad2fa9d1ecb1b |
| Llama-3.3-70B | 1.98 | Not recorded | 696dba60e25ad2fa9d1ecb1b |

### DREEAM-DOREMI

Precision: 79.39. Result ID: 699680315698665ec4c83043.

[Reporting paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

Recorded evaluation configuration: {"Category":"RoBERTa","Backbone":"RoBERTa","Training Strategy":"DOREMI iterative training"}. This record does not assert independent reproduction.

### DREEAM-DOREMI

Precision: 77.01. Result ID: 699680315698665ec4c83041.

[Reporting paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

Recorded evaluation configuration: {"Category":"BERT","Backbone":"BERT","Training Strategy":"DOREMI iterative training"}. This record does not assert independent reproduction.

### ATLOP-DOREMI

Precision: 74.86. Result ID: 699680315698665ec4c83042.

[Reporting paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

Recorded evaluation configuration: {"Category":"RoBERTa","Backbone":"RoBERTa","Training Strategy":"DOREMI iterative training"}. This record does not assert independent reproduction.

### ATLOP-DOREMI

Precision: 74.8. Result ID: 699680315698665ec4c83040.

[Reporting paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

Recorded evaluation configuration: {"Category":"BERT","Backbone":"BERT","Training Strategy":"DOREMI iterative training"}. This record does not assert independent reproduction.

### GPT-4.1

Precision: 16.12. Result ID: 699680315698665ec4c8303e.

[Reporting paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Category":"LLMs","Zero-shot":true,"Temperature":0.75}. This record does not assert independent reproduction.

### Llama-3.3-70B

Precision: 1.98. Result ID: 699680315698665ec4c8303f.

[Reporting paper](<https://www.sota2.com/research/paper/696dba60e25ad2fa9d1ecb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Category":"LLMs","Zero-shot":true,"Temperature":0.7}. This record does not assert independent reproduction.

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