# Document Question Answering on TriviaQA (EM, F1)

Source: [Document Question Answering on TriviaQA (EM, F1)](<https://www.sota2.com/research/sota/document-question-answering-on-triviaqa-em-f1>)

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

Data updated: 2026-05-08T10:07:56.701Z

Evaluation of model performance on the TriviaQA dataset for Document Question Answering, reporting Exact Match (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 | Document Question Answering |
| Dataset (including any stated split) | TriviaQA |
| Metric | EM |
| Unit | PERCENT |
| 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

- [EM](<https://www.sota2.com/research/sota/document-question-answering-on-triviaqa-em-f1.md?metric=EM>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/document-question-answering-on-triviaqa-em-f1.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| TaskFT-SPEED-28+BoS | 80.9 | Not recorded | 69fd6e155497b3b670c8941a |
| TaskFT-SPEED-24+BoS | 80.3 | Not recorded | 69fd6e155497b3b670c8941a |
| TaskFT-Full | 79.6 | Not recorded | 69fd6e155497b3b670c8941a |
| TaskFT-SPEED-20+BoS | 78.5 | Not recorded | 69fd6e155497b3b670c8941a |

### TaskFT-SPEED-28+BoS

EM: 80.9. Result ID: 69fdb4e547f34ce924e12b40.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

Recorded evaluation configuration: {"Fine-tuning":"Task-adaptive","K":"28","BoS":"true"}. This record does not assert independent reproduction.

### TaskFT-SPEED-24+BoS

EM: 80.3. Result ID: 69fdb4e547f34ce924e12b41.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

Recorded evaluation configuration: {"Fine-tuning":"Task-adaptive","K":"24","BoS":"true"}. This record does not assert independent reproduction.

### TaskFT-Full

EM: 79.6. Result ID: 69fdb4e547f34ce924e12b3f.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

Recorded evaluation configuration: {"Fine-tuning":"Task-adaptive","Visibility Policy":"Full"}. This record does not assert independent reproduction.

### TaskFT-SPEED-20+BoS

EM: 78.5. Result ID: 69fdb4e547f34ce924e12b42.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e155497b3b670c8941a.md>)

Recorded evaluation configuration: {"Fine-tuning":"Task-adaptive","K":"20","BoS":"true"}. This record does not assert independent reproduction.

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