# Medical Visual Question Answering on RAD-VQA

Source: [Medical Visual Question Answering on RAD-VQA](<https://www.sota2.com/research/sota/medical-visual-question-answering-on-rad-vqa>)

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

Data updated: 2026-05-07T07:25:50.050Z

Evaluation of model performance on the RAD-VQA dataset for Medical Visual Question Answering, reporting BERTScore.

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 | Medical Visual Question Answering |
| Dataset (including any stated split) | RAD-VQA |
| Metric | BERTScore |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [BERTScore](<https://www.sota2.com/research/sota/medical-visual-question-answering-on-rad-vqa.md?metric=BERTScore>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BERTScore | Result date | Report paper |
| --- | --- | --- | --- |
| Rform + Rexact + RDTW | 0.863 | Not recorded | 69fc1c7d5497b3b670c88460 |
| Rform + Rexact | 0.858 | Not recorded | 69fc1c7d5497b3b670c88460 |
| SFT | 0.813 | Not recorded | 69fc1c7d5497b3b670c88460 |
| Rform | 0.799 | Not recorded | 69fc1c7d5497b3b670c88460 |

### Rform + Rexact + RDTW

BERTScore: 0.863. Result ID: 69fc3dd347f34ce924de92b2.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

Recorded evaluation configuration: {"Training Strategy":"Formulaic + Exact Match + DTW reward training"}. This record does not assert independent reproduction.

### Rform + Rexact

BERTScore: 0.858. Result ID: 69fc3dd347f34ce924de92b1.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

Recorded evaluation configuration: {"Training Strategy":"Formulaic + Exact Match reward training"}. This record does not assert independent reproduction.

### SFT

BERTScore: 0.813. Result ID: 69fc3dd347f34ce924de92af.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

Recorded evaluation configuration: {"Training Strategy":"Supervised Fine-Tuning"}. This record does not assert independent reproduction.

### Rform

BERTScore: 0.799. Result ID: 69fc3dd347f34ce924de92b0.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1c7d5497b3b670c88460.md>)

Recorded evaluation configuration: {"Training Strategy":"Formulaic reward training"}. This record does not assert independent reproduction.

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