# Closed-book Question Answering on Natural Questions (NQ)

Source: [Closed-book Question Answering on Natural Questions (NQ)](<https://www.sota2.com/research/sota/closed-book-question-answering-on-natural-questions-nq>)

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

Data updated: 2026-03-18T07:46:21.980Z

Evaluation of Closed-book Question Answering performance on the Natural Questions (NQ) dataset, measured using Recall.

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 | Question Answer |
| Dataset (including any stated split) | Natural Questions (NQ) Closed-book |
| Metric | Recall |
| 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

- [Recall](<https://www.sota2.com/research/sota/closed-book-question-answering-on-natural-questions-nq.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall | Result date | Report paper |
| --- | --- | --- | --- |
| DoLA | 63.8 | Not recorded | 68fa7bcb1e209131cea8a81c |
| Greedy | 63.6 | Not recorded | 68fa7bcb1e209131cea8a81c |
| AGDLRPh | 63 | Not recorded | 68fa7bcb1e209131cea8a81c |
| Nucleus | 59.9 | Not recorded | 68fa7bcb1e209131cea8a81c |

### DoLA

Recall: 63.8. Result ID: 69ba583447f34ce924a3eb28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bcb1e209131cea8a81c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56577.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1 (8B)"}. This record does not assert independent reproduction.

### Greedy

Recall: 63.6. Result ID: 69ba583447f34ce924a3eb26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bcb1e209131cea8a81c.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1 (8B)"}. This record does not assert independent reproduction.

### AGDLRPh

Recall: 63. Result ID: 69ba583447f34ce924a3eb29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bcb1e209131cea8a81c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bcb1e209131cea8a81c.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1 (8B)"}. This record does not assert independent reproduction.

### Nucleus

Recall: 59.9. Result ID: 69ba583447f34ce924a3eb27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bcb1e209131cea8a81c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67041e209131cea13c72.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1 (8B)"}. This record does not assert independent reproduction.

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