# WSI Report Generation on TCGA-based dataset (test)

Source: [WSI Report Generation on TCGA-based dataset (test)](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test>)

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

Data updated: 2026-02-26T05:37:13.347Z

Evaluation of Whole Slide Image (WSI) report generation performance on the test split of a TCGA-based dataset, measured using text generation metrics (BLEU, METEOR, ROUGE).

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 | WSI Report Generation |
| Dataset (including any stated split) | TCGA-based dataset (test) |
| Metric | BLEU-1 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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

- [BLEU-1](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test.md?metric=BLEU-1>): Higher is better; unit: SCALAR.

- [BLEU-2](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test.md?metric=BLEU-2>): Higher is better; unit: SCALAR.

- [BLEU-3](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test.md?metric=BLEU-3>): Higher is better; unit: SCALAR.

- [BLEU-4](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test.md?metric=BLEU-4>): Higher is better; unit: SCALAR.

- [METEOR](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test.md?metric=METEOR>): Higher is better; unit: SCALAR.

- [ROUGE-L](<https://www.sota2.com/research/sota/wsi-report-generation-on-tcga-based-dataset-test.md?metric=ROUGE-L>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BLEU-1 | Result date | Report paper |
| --- | --- | --- | --- |
| HistGen | 0.413 | Not recorded | 68fa73a81e209131cea5dba9 |
| Transformer | 0.382 | Not recorded | 68fa73a81e209131cea5dba9 |
| R2GenCMN | 0.381 | Not recorded | 68fa73a81e209131cea5dba9 |
| M2Transformer | 0.321 | Not recorded | 68fa73a81e209131cea5dba9 |
| UpDownAttn | 0.32 | Not recorded | 68fa73a81e209131cea5dba9 |
| R2Gen | 0.274 | Not recorded | 68fa73a81e209131cea5dba9 |
| Transformer | 0.271 | Not recorded | 68fa73a81e209131cea5dba9 |
| Show&Tell | 0.262 | Not recorded | 68fa73a81e209131cea5dba9 |
| M2Transformer | 0.259 | Not recorded | 68fa73a81e209131cea5dba9 |
| UpDownAttn | 0.25 | Not recorded | 68fa73a81e209131cea5dba9 |
| M2Transformer | 0.25 | Not recorded | 68fa73a81e209131cea5dba9 |
| Show&Tell | 0.249 | Not recorded | 68fa73a81e209131cea5dba9 |
| Transformer | 0.249 | Not recorded | 68fa73a81e209131cea5dba9 |
| R2Gen | 0.24 | Not recorded | 68fa73a81e209131cea5dba9 |
| UpDownAttn | 0.24 | Not recorded | 68fa73a81e209131cea5dba9 |
| R2Gen | 0.237 | Not recorded | 68fa73a81e209131cea5dba9 |
| R2GenCMN | 0.225 | Not recorded | 68fa73a81e209131cea5dba9 |
| R2GenCMN | 0.211 | Not recorded | 68fa73a81e209131cea5dba9 |
| Show&Tell | 0.189 | Not recorded | 68fa73a81e209131cea5dba9 |

### HistGen

BLEU-1: 0.413. Result ID: 6992fd4f3a6c31484912e3d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Implementation](<https://github.com/dddavid4real/HistGen>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

### Transformer

BLEU-1: 0.382. Result ID: 6992fd4f3a6c31484912e3ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

### R2GenCMN

BLEU-1: 0.381. Result ID: 6992fd4f3a6c31484912e3d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33abf.md>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

### M2Transformer

BLEU-1: 0.321. Result ID: 6992fd4f3a6c31484912e3cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67421e209131cea154e2.md>)

[Implementation](<https://github.com/aimagelab/meshed-memory-transformer>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

### UpDownAttn

BLEU-1: 0.32. Result ID: 6992fd4f3a6c31484912e3cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642b1e209131cea031b7.md>)

[Implementation](<http://www.panderson.me/up-down-attention>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

### R2Gen

BLEU-1: 0.274. Result ID: 6992fd4f3a6c31484912e3d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c6a1e209131cea33f6c.md>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

### Transformer

BLEU-1: 0.271. Result ID: 6992fd4f3a6c31484912e3c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Feature Extractor":"CTransPath"}. This record does not assert independent reproduction.

### Show&Tell

BLEU-1: 0.262. Result ID: 6992fd4f3a6c31484912e3c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61cd1e209131ce9f60d4.md>)

[Implementation](<http://nic.droppages.com/>)

Recorded evaluation configuration: {"Feature Extractor":"CTransPath"}. This record does not assert independent reproduction.

### M2Transformer

BLEU-1: 0.259. Result ID: 6992fd4f3a6c31484912e3c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67421e209131cea154e2.md>)

[Implementation](<https://github.com/aimagelab/meshed-memory-transformer>)

Recorded evaluation configuration: {"Feature Extractor":"CTransPath"}. This record does not assert independent reproduction.

### UpDownAttn

BLEU-1: 0.25. Result ID: 6992fd4f3a6c31484912e3c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642b1e209131cea031b7.md>)

[Implementation](<http://www.panderson.me/up-down-attention>)

Recorded evaluation configuration: {"Feature Extractor":"ResNet50"}. This record does not assert independent reproduction.

### M2Transformer

BLEU-1: 0.25. Result ID: 6992fd4f3a6c31484912e3c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67421e209131cea154e2.md>)

[Implementation](<https://github.com/aimagelab/meshed-memory-transformer>)

Recorded evaluation configuration: {"Feature Extractor":"ResNet50"}. This record does not assert independent reproduction.

### Show&Tell

BLEU-1: 0.249. Result ID: 6992fd4f3a6c31484912e3c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61cd1e209131ce9f60d4.md>)

[Implementation](<http://nic.droppages.com/>)

Recorded evaluation configuration: {"Feature Extractor":"ResNet50"}. This record does not assert independent reproduction.

### Transformer

BLEU-1: 0.249. Result ID: 6992fd4f3a6c31484912e3c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Feature Extractor":"ResNet50"}. This record does not assert independent reproduction.

### R2Gen

BLEU-1: 0.24. Result ID: 6992fd4f3a6c31484912e3c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c6a1e209131cea33f6c.md>)

Recorded evaluation configuration: {"Feature Extractor":"ResNet50"}. This record does not assert independent reproduction.

### UpDownAttn

BLEU-1: 0.24. Result ID: 6992fd4f3a6c31484912e3c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642b1e209131cea031b7.md>)

[Implementation](<http://www.panderson.me/up-down-attention>)

Recorded evaluation configuration: {"Feature Extractor":"CTransPath"}. This record does not assert independent reproduction.

### R2Gen

BLEU-1: 0.237. Result ID: 6992fd4f3a6c31484912e3ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c6a1e209131cea33f6c.md>)

Recorded evaluation configuration: {"Feature Extractor":"CTransPath"}. This record does not assert independent reproduction.

### R2GenCMN

BLEU-1: 0.225. Result ID: 6992fd4f3a6c31484912e3c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33abf.md>)

Recorded evaluation configuration: {"Feature Extractor":"ResNet50"}. This record does not assert independent reproduction.

### R2GenCMN

BLEU-1: 0.211. Result ID: 6992fd4f3a6c31484912e3cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33abf.md>)

Recorded evaluation configuration: {"Feature Extractor":"CTransPath"}. This record does not assert independent reproduction.

### Show&Tell

BLEU-1: 0.189. Result ID: 6992fd4f3a6c31484912e3cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5dba9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61cd1e209131ce9f60d4.md>)

[Implementation](<http://nic.droppages.com/>)

Recorded evaluation configuration: {"Feature Extractor":"DINOv2 ViT-L"}. This record does not assert independent reproduction.

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