# Cascading Dialogue Success on ABCD (test)

Source: [Cascading Dialogue Success on ABCD (test)](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test>)

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

Data updated: 2026-02-26T05:47:16.067Z

Evaluation of Cascading Dialogue Success performance on the test split of the ABCD 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 | Cascading Dialogue Success |
| Dataset (including any stated split) | ABCD (test) |
| Metric | Intent 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

- [Intent Accuracy](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test.md?metric=Intent%20Accuracy>): Higher is better; unit: PERCENT.

- [Next Step Success](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test.md?metric=Next%20Step%20Success>): Higher is better; unit: PERCENT.

- [Slot Filling Accuracy](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test.md?metric=Slot%20Filling%20Accuracy>): Higher is better; unit: PERCENT.

- [Value Extraction Accuracy](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test.md?metric=Value%20Extraction%20Accuracy>): Higher is better; unit: PERCENT.

- [Recall@1](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test.md?metric=Recall%401>): Higher is better; unit: PERCENT.

- [Cross Entropy](<https://www.sota2.com/research/sota/cascading-dialogue-success-on-abcd-test.md?metric=Cross%20Entropy>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Intent Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ABCD Ensemble | 90.5 | Not recorded | 68fa6e901e209131cea40acb |
| CDS-T5-Base | 86 | Not recorded | 68fa6e901e209131cea40acb |
| CDS-T5-Small | 85.7 | Not recorded | 68fa6e901e209131cea40acb |

### ABCD Ensemble

Intent Accuracy: 90.5. Result ID: 699047e73a6c314849ff71e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40acb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea23870.md>)

Recorded evaluation configuration: {"Params":"345M"}. This record does not assert independent reproduction.

### CDS-T5-Base

Intent Accuracy: 86. Result ID: 699047e73a6c314849ff71e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40acb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40acb.md>)

[Implementation](<https://github.com/ServiceNow/research-workflow-discovery>)

Recorded evaluation configuration: {"Params":"220M"}. This record does not assert independent reproduction.

### CDS-T5-Small

Intent Accuracy: 85.7. Result ID: 699047e73a6c314849ff71e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40acb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40acb.md>)

[Implementation](<https://github.com/ServiceNow/research-workflow-discovery>)

Recorded evaluation configuration: {"Params":"60M"}. This record does not assert independent reproduction.

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