# Continual Knowledge Incorporation on SQuAD 100 passages (val)

Source: [Continual Knowledge Incorporation on SQuAD 100 passages (val)](<https://www.sota2.com/research/sota/continual-knowledge-incorporation-on-squad-100-passages-val>)

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

Data updated: 2026-05-11T08:09:16.557Z

Evaluation of a model's ability to incorporate new knowledge continuously on the 100-passage validation subset of the SQuAD dataset, measured by Immediate Accuracy and Retention.

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 Knowledge Incorporation |
| Dataset (including any stated split) | SQuAD 100 passages (val) |
| Metric | Immediate Accuracy |
| 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

- [Immediate Accuracy](<https://www.sota2.com/research/sota/continual-knowledge-incorporation-on-squad-100-passages-val.md?metric=Immediate%20Accuracy>): Higher is better; unit: PERCENT.

- [Retention](<https://www.sota2.com/research/sota/continual-knowledge-incorporation-on-squad-100-passages-val.md?metric=Retention>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Immediate Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SCoL | 35.4 | Not recorded | 6a016297dbc836b87d823165 |
| SCoL | 34.3 | Not recorded | 6a016297dbc836b87d823165 |
| Prompting-only | 28.17 | Not recorded | 6a016297dbc836b87d823165 |
| Batch TTT | 26.52 | Not recorded | 6a016297dbc836b87d823165 |
| SEALcontinual | 13.7 | Not recorded | 6a016297dbc836b87d823165 |

### SCoL

Immediate Accuracy: 35.4. Result ID: 6a018e9747f34ce924e33fc6.

[Reporting paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

Recorded evaluation configuration: {"lambda":"1"}. This record does not assert independent reproduction.

### SCoL

Immediate Accuracy: 34.3. Result ID: 6a018e9747f34ce924e33fc5.

[Reporting paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

Recorded evaluation configuration: {"lambda":"0"}. This record does not assert independent reproduction.

### Prompting-only

Immediate Accuracy: 28.17. Result ID: 6a018e9747f34ce924e33fc2.

[Reporting paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

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

### Batch TTT

Immediate Accuracy: 26.52. Result ID: 6a018e9747f34ce924e33fc3.

[Reporting paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

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

### SEALcontinual

Immediate Accuracy: 13.7. Result ID: 6a018e9747f34ce924e33fc4.

[Reporting paper](<https://www.sota2.com/research/paper/6a016297dbc836b87d823165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b5f1e209131cea87fde.md>)

Recorded evaluation configuration: {"procedure":"Continual LoRA fine-tuning"}. This record does not assert independent reproduction.

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