# Closed book Question Answering on MultiSpanQA (test)

Source: [Closed book Question Answering on MultiSpanQA (test)](<https://www.sota2.com/research/sota/closed-book-question-answering-on-multispanqa-test>)

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

Data updated: 2026-02-26T05:43:17.751Z

Evaluation of model performance on the test split of the MultiSpanQA dataset for Closed book Question Answering.

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 | Closed book Question Answering |
| Dataset (including any stated split) | MultiSpanQA (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

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

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

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

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| CoVe (factored) | 48 | Not recorded | 68fa70b41e209131cea4cb37 |
| CoVe (joint) | 46 | Not recorded | 68fa70b41e209131cea4cb37 |
| Llama 65B (Few-shot) | 39 | Not recorded | 68fa70b41e209131cea4cb37 |
| Llama 2 70B Chat (Zero-shot) | 20 | Not recorded | 68fa70b41e209131cea4cb37 |
| Llama 2 70B Chat (CoT) | 17 | Not recorded | 68fa70b41e209131cea4cb37 |

### CoVe (factored)

F1 Score: 48. Result ID: 699154bb3a6c314849075d74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

Recorded evaluation configuration: {"LLM":"Llama 65B","Strategy":"CoVe (factored)"}. This record does not assert independent reproduction.

### CoVe (joint)

F1 Score: 46. Result ID: 699154bb3a6c314849075d73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

Recorded evaluation configuration: {"LLM":"Llama 65B","Strategy":"CoVe (joint)"}. This record does not assert independent reproduction.

### Llama 65B (Few-shot)

F1 Score: 39. Result ID: 699154bb3a6c314849075d72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eae1e209131cea41685.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"LLM":"Llama 65B","Strategy":"Few-shot"}. This record does not assert independent reproduction.

### Llama 2 70B Chat (Zero-shot)

F1 Score: 20. Result ID: 699154bb3a6c314849075d70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"LLM":"Llama 2 70B Chat","Strategy":"Zero-shot"}. This record does not assert independent reproduction.

### Llama 2 70B Chat (CoT)

F1 Score: 17. Result ID: 699154bb3a6c314849075d71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"LLM":"Llama 2 70B Chat","Strategy":"CoT"}. This record does not assert independent reproduction.

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