# Commonsense Knowledge Generation on ATOMIC 2019 (test)

Source: [Commonsense Knowledge Generation on ATOMIC 2019 (test)](<https://www.sota2.com/research/sota/commonsense-knowledge-generation-on-atomic-2019-test>)

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

Data updated: 2026-02-26T05:55:09.680Z

Evaluation of model performance on commonsense knowledge generation using the test split of the ATOMIC 2019 dataset, measured by metrics like Perplexity (PPL) and DS.

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 | Commonsense Knowledge Generation |
| Dataset (including any stated split) | ATOMIC 2019 (test) |
| Metric | PPL |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [PPL](<https://www.sota2.com/research/sota/commonsense-knowledge-generation-on-atomic-2019-test.md?metric=PPL>): Lower is better; unit: SCALAR.

- [DS](<https://www.sota2.com/research/sota/commonsense-knowledge-generation-on-atomic-2019-test.md?metric=DS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PPL | Result date | Report paper |
| --- | --- | --- | --- |
| COMETours | 11.11 | Not recorded | 68fa6f761e209131cea45bc2 |
| COMET | 11.14 | Not recorded | 68fa6f761e209131cea45bc2 |

### COMETours

PPL: 11.11. Result ID: 6990c10e3a6c314849030337.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f761e209131cea45bc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f761e209131cea45bc2.md>)

[Implementation](<https://github.com/NUSTM/Dense-ATOMIC>)

Recorded evaluation configuration: {"Training Data":"Dense-ATOMIC"}. This record does not assert independent reproduction.

### COMET

PPL: 11.14. Result ID: 6990c10e3a6c314849030336.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f761e209131cea45bc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65de1e209131cea0cf99.md>)

Recorded evaluation configuration: {"Training Data":"ATOMIC"}. This record does not assert independent reproduction.

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