# Task-oriented dialogue on In-car personal assistant dialogue dataset (test)

Source: [Task-oriented dialogue on In-car personal assistant dialogue dataset (test)](<https://www.sota2.com/research/sota/task-oriented-dialogue-on-in-car-personal-assistant-dialogue-dataset-test>)

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

Data updated: 2026-02-26T05:39:53.605Z

Evaluation of Task-oriented Dialogue performance on the test split of the In-car personal assistant dialogue dataset, measured using subjective metrics such as Correctness, Appropriateness, and Humanlikeness.

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 | Task-oriented dialogue |
| Dataset (including any stated split) | In-car personal assistant dialogue dataset (test) |
| Metric | Correctness |
| Unit | SCALAR |
| 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

- [Correctness](<https://www.sota2.com/research/sota/task-oriented-dialogue-on-in-car-personal-assistant-dialogue-dataset-test.md?metric=Correctness>): Higher is better; unit: SCALAR.

- [Appropriateness](<https://www.sota2.com/research/sota/task-oriented-dialogue-on-in-car-personal-assistant-dialogue-dataset-test.md?metric=Appropriateness>): Higher is better; unit: SCALAR.

- [Humanlikeness](<https://www.sota2.com/research/sota/task-oriented-dialogue-on-in-car-personal-assistant-dialogue-dataset-test.md?metric=Humanlikeness>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Correctness | Result date | Report paper |
| --- | --- | --- | --- |
| Rule-based | 3.96 | Not recorded | 68fa63841e209131ce9ff2fe |
| KV Ret. Net | 3.7 | Not recorded | 68fa63841e209131ce9ff2fe |
| Copy Net | 3.52 | Not recorded | 68fa63841e209131ce9ff2fe |

### Rule-based

Correctness: 3.96. Result ID: 698bf7b5f729bc7f68e6f214.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63841e209131ce9ff2fe.md>)

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

### KV Ret. Net

Correctness: 3.7. Result ID: 698bf7b5f729bc7f68e6f216.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63841e209131ce9ff2fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63841e209131ce9ff2fe.md>)

[Implementation](<https://nlp.stanford.edu/blog/a-new-multi-turn-multi-domain-task-oriented-dialogue-dataset/>)

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

### Copy Net

Correctness: 3.52. Result ID: 698bf7b5f729bc7f68e6f215.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63841e209131ce9ff2fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63881e209131ce9ff57c.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.