# Document Based Question Answering on nlpcc-dbqa (test)

Source: [Document Based Question Answering on nlpcc-dbqa (test)](<https://www.sota2.com/research/sota/document-based-question-answering-on-nlpcc-dbqa-test>)

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

Data updated: 2026-02-26T05:50:20.091Z

Evaluation of model performance on the test split of the nlpcc-dbqa dataset for Document Based Question Answering, reporting MRR 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 Based Question Answering |
| Dataset (including any stated split) | nlpcc-dbqa (test) |
| Metric | MRR |
| 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

- [MRR](<https://www.sota2.com/research/sota/document-based-question-answering-on-nlpcc-dbqa-test.md?metric=MRR>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/document-based-question-answering-on-nlpcc-dbqa-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MRR | Result date | Report paper |
| --- | --- | --- | --- |
| ERNIE 2.0 | 95.8 | Not recorded | 68fa66ad1e209131cea11a4d |
| ERNIE 2.0 | 95.7 | Not recorded | 68fa66ad1e209131cea11a4d |
| ERNIE | 95.1 | Not recorded | 68fa65ac1e209131cea0bd99 |
| ERNIE 1.0 | 95.1 | Not recorded | 68fa66ad1e209131cea11a4d |
| BERT | 94.6 | Not recorded | 68fa65ac1e209131cea0bd99 |
| BERT | 94.6 | Not recorded | 68fa66ad1e209131cea11a4d |

### ERNIE 2.0

MRR: 95.8. Result ID: 698d00d68b517eb4331e49ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a4d.md>)

[Implementation](<https://github.com/PaddlePaddle/ERNIE>)

Recorded evaluation configuration: {"Model Version":"ERNIE 2.0","Model Scale":"LARGE"}. This record does not assert independent reproduction.

### ERNIE 2.0

MRR: 95.7. Result ID: 698d00d68b517eb4331e49c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a4d.md>)

[Implementation](<https://github.com/PaddlePaddle/ERNIE>)

Recorded evaluation configuration: {"Model Version":"ERNIE 2.0","Model Scale":"BASE"}. This record does not assert independent reproduction.

### ERNIE

MRR: 95.1. Result ID: 698cc2b48b517eb4331c8f02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bd99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bd99.md>)

[Implementation](<https://github.com/PaddlePaddle/LARK/tree/develop/ERNIE>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ERNIE 1.0

MRR: 95.1. Result ID: 698d00d68b517eb4331e49c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bd99.md>)

[Implementation](<https://github.com/PaddlePaddle/LARK/tree/develop/ERNIE>)

Recorded evaluation configuration: {"Model Version":"ERNIE 1.0","Model Scale":"BASE"}. This record does not assert independent reproduction.

### BERT

MRR: 94.6. Result ID: 698cc2b48b517eb4331c8f01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65ac1e209131cea0bd99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BERT

MRR: 94.6. Result ID: 698d00d68b517eb4331e49c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a4d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Model Version":"BERT","Model Scale":"BASE"}. This record does not assert independent reproduction.

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