# Open-ended Question Answering on NarrativeQA (Acc, BLEU, F1)

Source: [Open-ended Question Answering on NarrativeQA (Acc, BLEU, F1)](<https://www.sota2.com/research/sota/open-ended-question-answering-on-narrativeqa-acc-bleu-f1>)

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

Data updated: 2026-05-22T07:36:26.094Z

Evaluation of Open-ended Question Answering performance on the NarrativeQA dataset, reporting Accuracy, BLEU, 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 | Open-ended Question Answering |
| Dataset (including any stated split) | NarrativeQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/open-ended-question-answering-on-narrativeqa-acc-bleu-f1.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [BLEU Score](<https://www.sota2.com/research/sota/open-ended-question-answering-on-narrativeqa-acc-bleu-f1.md?metric=BLEU%20Score>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| w/t BoT | 73.77 | Not recorded | 6a0fe31ef984739ed6739dd5 |
| w/t CD | 72.59 | Not recorded | 6a0fe31ef984739ed6739dd5 |
| w/t KLE | 72.03 | Not recorded | 6a0fe31ef984739ed6739dd5 |
| w/t SE | 71.76 | Not recorded | 6a0fe31ef984739ed6739dd5 |
| CARE | 71.4 | Not recorded | 6a0fe31ef984739ed6739dd5 |
| GRPO | 66.23 | Not recorded | 6a0fe31ef984739ed6739dd5 |
| EMPO | 57.38 | Not recorded | 6a0fe31ef984739ed6739dd5 |

### w/t BoT

Accuracy: 73.77. Result ID: 6a100776fbc373592c08a719.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct","Geometric Component":"Barycentric Transport"}. This record does not assert independent reproduction.

### w/t CD

Accuracy: 72.59. Result ID: 6a100776fbc373592c08a718.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct","Geometric Component":"Cosine Dispersion"}. This record does not assert independent reproduction.

### w/t KLE

Accuracy: 72.03. Result ID: 6a100776fbc373592c08a715.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73601e209131cea5c05e.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct"}. This record does not assert independent reproduction.

### w/t SE

Accuracy: 71.76. Result ID: 6a100776fbc373592c08a714.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789a1e209131cea793ec.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct"}. This record does not assert independent reproduction.

### CARE

Accuracy: 71.4. Result ID: 6a100776fbc373592c08a717.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79901e209131cea7e41e.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct"}. This record does not assert independent reproduction.

### GRPO

Accuracy: 66.23. Result ID: 6a100776fbc373592c08a713.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct"}. This record does not assert independent reproduction.

### EMPO

Accuracy: 57.38. Result ID: 6a100776fbc373592c08a716.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe31ef984739ed6739dd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78961e209131cea791f6.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5b-instruct"}. This record does not assert independent reproduction.

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