# Continual Learning on Narrative Abstraction Benchmark (NAB) known stories

Source: [Continual Learning on Narrative Abstraction Benchmark (NAB) known stories](<https://www.sota2.com/research/sota/continual-learning-on-narrative-abstraction-benchmark-nab-known-stories>)

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

Data updated: 2026-03-19T08:12:26.523Z

Evaluation of Continual Learning performance using Cumulative Accuracy and Forgetting metrics on the Narrative Abstraction Benchmark (NAB) known stories dataset.

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 | Continual Learning |
| Dataset (including any stated split) | Narrative Abstraction Benchmark (NAB) known stories |
| Metric | Cumulative Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Cumulative Accuracy](<https://www.sota2.com/research/sota/continual-learning-on-narrative-abstraction-benchmark-nab-known-stories.md?metric=Cumulative%20Accuracy>): Higher is better; unit: PERCENT.

- [Forgetting](<https://www.sota2.com/research/sota/continual-learning-on-narrative-abstraction-benchmark-nab-known-stories.md?metric=Forgetting>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Cumulative Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Buffer-100 | 89.4 | Not recorded | 69bb82f20636e5bf4afc191e |
| AAT | 86.83 | Not recorded | 69bb82f20636e5bf4afc191e |
| Normal SFT | 86.74 | Not recorded | 69bb82f20636e5bf4afc191e |

### Buffer-100

Cumulative Accuracy: 89.4. Result ID: 69bbaf7a47f34ce924a56939.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82f20636e5bf4afc191e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cf21e209131cea36bdf.md>)

Recorded evaluation configuration: {"Buffer size":"100"}. This record does not assert independent reproduction.

### AAT

Cumulative Accuracy: 86.83. Result ID: 69bbaf7a47f34ce924a5693a.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82f20636e5bf4afc191e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb82f20636e5bf4afc191e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Normal SFT

Cumulative Accuracy: 86.74. Result ID: 69bbaf7a47f34ce924a56938.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82f20636e5bf4afc191e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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