# Knowledge-based Visual Question Answering on E-VQA (test)

Source: [Knowledge-based Visual Question Answering on E-VQA (test)](<https://www.sota2.com/research/sota/knowledge-based-visual-question-answering-on-e-vqa-test>)

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

Data updated: 2026-02-26T05:30:13.718Z

Evaluation of model performance on the test split of the E-VQA dataset for Knowledge-based Visual Question Answering.

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-based Visual Question Answering |
| Dataset (including any stated split) | E-VQA (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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-based-visual-question-answering-on-e-vqa-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LamRA | 56.2 | Not recorded | 68fa76081e209131cea6b06a |
| RA-VQAv2 w/ PreFLMR | 54.5 | Not recorded | 68fa76081e209131cea6b06a |

### LamRA

Accuracy: 56.2. Result ID: 699422203a6c3148491b4899.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76081e209131cea6b06a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76081e209131cea6b06a.md>)

[Implementation](<https://code-kunkun.github.io/LamRA/>)

Recorded evaluation configuration: {"Training":"Simultaneous retrieval and VQA using LoRA"}. This record does not assert independent reproduction.

### RA-VQAv2 w/ PreFLMR

Accuracy: 54.5. Result ID: 699422203a6c3148491b4898.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76081e209131cea6b06a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e8b5.md>)

[Implementation](<https://github.com/LinWeizheDragon/Retrieval-Augmented-Visual-Question-Answering>)

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

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