# Knowledge Base Question Answering on CWQ (hidden test)

Source: [Knowledge Base Question Answering on CWQ (hidden test)](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-cwq-hidden-test>)

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

Data updated: 2026-02-26T05:28:04.883Z

Evaluation of Knowledge Base Question Answering performance on the hidden test split of the Complex WebQuestions (CWQ) dataset.

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 | Knowledge Base Question Answering |
| Dataset (including any stated split) | CWQ (hidden test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-cwq-hidden-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-cwq-hidden-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/knowledge-base-question-answering-on-cwq-hidden-test.md?metric=Recall>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CBR-KBQA | 67.1 | Not recorded | 68fa6b331e209131cea2ccf9 |
| T5-11B | 55.6 | Not recorded | 68fa6b331e209131cea2ccf9 |
| T5-11B | 52.4 | Not recorded | 68fa6b331e209131cea2ccf9 |
| DynAS | 50 | Not recorded | 68fa6b331e209131cea2ccf9 |
| PullNet | 45.9 | Not recorded | 68fa6b331e209131cea2ccf9 |
| QGG | 44.1 | Not recorded | 68fa6b331e209131cea2ccf9 |
| KBQA-GST | 39.4 | Not recorded | 68fa6b331e209131cea2ccf9 |

### CBR-KBQA

Accuracy: 67.1. Result ID: 698e6fe2ffc3901de09d97f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

Recorded evaluation configuration: {"Supervision level":"Supervised"}. This record does not assert independent reproduction.

### T5-11B

Accuracy: 55.6. Result ID: 698e6fe2ffc3901de09d97f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Supervision level":"Supervised","Revise step":true}. This record does not assert independent reproduction.

### T5-11B

Accuracy: 52.4. Result ID: 698e6fe2ffc3901de09d97ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Supervision level":"Supervised","Revise step":false}. This record does not assert independent reproduction.

### DynAS

Accuracy: 50. Result ID: 698e6fe2ffc3901de09d97ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

Recorded evaluation configuration: {"Supervision level":"Weekly supervised","Organization":"Alibaba Group"}. This record does not assert independent reproduction.

### PullNet

Accuracy: 45.9. Result ID: 698e6fe2ffc3901de09d97ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a81e209131cea0bb2c.md>)

[Implementation](<https://github.com/OceanskySun/GraftNet>)

Recorded evaluation configuration: {"Supervision level":"Weekly supervised"}. This record does not assert independent reproduction.

### QGG

Accuracy: 44.1. Result ID: 698e6fe2ffc3901de09d97ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

Recorded evaluation configuration: {"Supervision level":"Weekly supervised"}. This record does not assert independent reproduction.

### KBQA-GST

Accuracy: 39.4. Result ID: 698e6fe2ffc3901de09d97eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccf9.md>)

Recorded evaluation configuration: {"Supervision level":"Weekly supervised"}. This record does not assert independent reproduction.

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