# Generative Question Answering on NYT (test)

Source: [Generative Question Answering on NYT (test)](<https://www.sota2.com/research/sota/generative-question-answering-on-nyt-test>)

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

Data updated: 2026-02-26T05:41:33.291Z

Evaluation of model performance on the test split of the NYT dataset for Generative Question Answering, reporting EM 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 | Generative Question Answering |
| Dataset (including any stated split) | NYT (test) |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [EM](<https://www.sota2.com/research/sota/generative-question-answering-on-nyt-test.md?metric=EM>): Higher is better; unit: PERCENT.

- [F1](<https://www.sota2.com/research/sota/generative-question-answering-on-nyt-test.md?metric=F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| SWEP | 76.42 | Not recorded | 68fa6a381e209131cea26b40 |
| Prior-Aug | 75.52 | Not recorded | 68fa6a381e209131cea26b40 |
| MLE | 75.1 | Not recorded | 68fa6a381e209131cea26b40 |
| Gaussian-Dropout | 74.76 | Not recorded | 68fa6a381e209131cea26b40 |
| Word-Dropout | 74.27 | Not recorded | 68fa6a381e209131cea26b40 |
| Bernoulli-Dropout | 73.81 | Not recorded | 68fa6a381e209131cea26b40 |
| Adv-Aug | 73.46 | Not recorded | 68fa6a381e209131cea26b40 |
| SSMBA | 73.29 | Not recorded | 68fa6a381e209131cea26b40 |

### SWEP

EM: 76.42. Result ID: 698e1f23ffc3901de09af462.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### Prior-Aug

EM: 75.52. Result ID: 698e1f23ffc3901de09af461.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### MLE

EM: 75.1. Result ID: 698e1f23ffc3901de09af45b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### Gaussian-Dropout

EM: 74.76. Result ID: 698e1f23ffc3901de09af45e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### Word-Dropout

EM: 74.27. Result ID: 698e1f23ffc3901de09af45d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa629f1e209131ce9fa496.md>)

[Implementation](<https://github.com/rsennrich/nematus>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### Bernoulli-Dropout

EM: 73.81. Result ID: 698e1f23ffc3901de09af45f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### Adv-Aug

EM: 73.46. Result ID: 698e1f23ffc3901de09af45c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64ff1e209131cea07ad5.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

### SSMBA

EM: 73.29. Result ID: 698e1f23ffc3901de09af460.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68701e209131cea1c379.md>)

Recorded evaluation configuration: {"Model Architecture":"T5-small"}. This record does not assert independent reproduction.

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