# Evidence Sentence Selection on DIALFACT (test)

Source: [Evidence Sentence Selection on DIALFACT (test)](<https://www.sota2.com/research/sota/evidence-sentence-selection-on-dialfact-test>)

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

Data updated: 2026-02-26T06:01:39.595Z

Evaluation of model performance on the test split of the DIALFACT dataset for the Evidence Sentence Selection task.

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 | Evidence Sentence Selection |
| Dataset (including any stated split) | DIALFACT (test) |
| Metric | Recall@5 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Recall@5](<https://www.sota2.com/research/sota/evidence-sentence-selection-on-dialfact-test.md?metric=Recall%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall@5 | Result date | Report paper |
| --- | --- | --- | --- |
| Ret-with-context | 75.4 | Not recorded | 68fa6c0f1e209131cea31ce6 |
| Ret-only-claim | 70.1 | Not recorded | 68fa6c0f1e209131cea31ce6 |
| Ret-with-context | 69.3 | Not recorded | 68fa6c0f1e209131cea31ce6 |
| Ret-only-claim | 67.1 | Not recorded | 68fa6c0f1e209131cea31ce6 |

### Ret-with-context

Recall@5: 75.4. Result ID: 698ec1ecffc3901de0a0d1ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Implementation](<https://github.com/salesforce/DialFact>)

Recorded evaluation configuration: {"Document Retrieval Source":"Wiki-ctx"}. This record does not assert independent reproduction.

### Ret-only-claim

Recall@5: 70.1. Result ID: 698ec1ecffc3901de0a0d1ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Implementation](<https://github.com/salesforce/DialFact>)

Recorded evaluation configuration: {"Document Retrieval Source":"Wiki-ctx"}. This record does not assert independent reproduction.

### Ret-with-context

Recall@5: 69.3. Result ID: 698ec1ecffc3901de0a0d1ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Implementation](<https://github.com/salesforce/DialFact>)

Recorded evaluation configuration: {"Document Retrieval Source":"DPR-WoWft-ctx"}. This record does not assert independent reproduction.

### Ret-only-claim

Recall@5: 67.1. Result ID: 698ec1ecffc3901de0a0d1ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31ce6.md>)

[Implementation](<https://github.com/salesforce/DialFact>)

Recorded evaluation configuration: {"Document Retrieval Source":"DPR-WoWft-ctx"}. This record does not assert independent reproduction.

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