# Explanation Attribution on SQuAD v1.1 (val)

Source: [Explanation Attribution on SQuAD v1.1 (val)](<https://www.sota2.com/research/sota/explanation-attribution-on-squad-v1-1-val>)

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

Data updated: 2026-02-26T05:21:40.931Z

Evaluation of model explanation attribution methods using metrics like Rank Stability (Spearman ρ) on the validation split of the Stanford Question Answering Dataset (SQuAD) version 1.1.

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 | Explanation Attribution |
| Dataset (including any stated split) | SQuAD v1.1 (val) |
| Metric | Spearman Rank Correlation (ρ) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 0 of 0 |
| 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

- [Spearman Rank Correlation (ρ)](<https://www.sota2.com/research/sota/explanation-attribution-on-squad-v1-1-val.md?metric=Spearman%20Rank%20Correlation%20(%CF%81)>): Higher is better; unit: SCALAR.

- [Top-5 Overlap](<https://www.sota2.com/research/sota/explanation-attribution-on-squad-v1-1-val.md?metric=Top-5%20Overlap>): Higher is better; unit: PERCENT.

- [Duplication Split Score](<https://www.sota2.com/research/sota/explanation-attribution-on-squad-v1-1-val.md?metric=Duplication%20Split%20Score>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Spearman Rank Correlation (ρ) | Result date | Report paper |
| --- | --- | --- | --- |

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