# Metaphor Detection on PSU CMC (test)

Source: [Metaphor Detection on PSU CMC (test)](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test>)

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

Data updated: 2026-05-11T08:29:30.316Z

Evaluation of Metaphor Detection performance on the test split of the PSU CMC dataset, focusing on various F1 scores including overall, macro, and domain-specific (Academic, Fiction, News) metrics.

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 | Metaphor Detection |
| Dataset (including any stated split) | PSU CMC (test) |
| Metric | Pos-F1 Score |
| 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

- [Pos-F1 Score](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=Pos-F1%20Score>): Higher is better; unit: PERCENT.

- [Macro F1 Score](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=Macro%20F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [Academic F1 Score](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=Academic%20F1%20Score>): Higher is better; unit: PERCENT.

- [Fiction F1 Score](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=Fiction%20F1%20Score>): Higher is better; unit: PERCENT.

- [News F1 Score](<https://www.sota2.com/research/sota/metaphor-detection-on-psu-cmc-test.md?metric=News%20F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pos-F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| MelBERT (MIP-only) | 72.81 | Not recorded | 6a016257dbc836b87d822eb8 |
| MelBERT (full) | 72.7 | Not recorded | 6a016257dbc836b87d822eb8 |
| RoBERTa-wwm-ext-large | 71.42 | Not recorded | 6a016257dbc836b87d822eb8 |
| Qwen3.5-9B (Q2 Generative) | 61.57 | Not recorded | 6a016257dbc836b87d822eb8 |

### MelBERT (MIP-only)

Pos-F1 Score: 72.81. Result ID: 6a01935347f34ce924e36502.

[Reporting paper](<https://www.sota2.com/research/paper/6a016257dbc836b87d822eb8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a016257dbc836b87d822eb8.md>)

Recorded evaluation configuration: {"Configuration":"MIP-only","Number of seeds":"5"}. This record does not assert independent reproduction.

### MelBERT (full)

Pos-F1 Score: 72.7. Result ID: 6a01935347f34ce924e36501.

[Reporting paper](<https://www.sota2.com/research/paper/6a016257dbc836b87d822eb8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a016257dbc836b87d822eb8.md>)

Recorded evaluation configuration: {"Configuration":"full","Number of seeds":"5"}. This record does not assert independent reproduction.

### RoBERTa-wwm-ext-large

Pos-F1 Score: 71.42. Result ID: 6a01935347f34ce924e36500.

[Reporting paper](<https://www.sota2.com/research/paper/6a016257dbc836b87d822eb8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b4f1e209131cea2d827.md>)

[Implementation](<https://github.com/ymcui/Chinese-BERT-wwm>)

Recorded evaluation configuration: {"Fine-tuning":"plain","Number of seeds":"5"}. This record does not assert independent reproduction.

### Qwen3.5-9B (Q2 Generative)

Pos-F1 Score: 61.57. Result ID: 6a01935347f34ce924e36503.

[Reporting paper](<https://www.sota2.com/research/paper/6a016257dbc836b87d822eb8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6a1e209131cea456e1.md>)

[Implementation](<https://github.com/artidoro/qlora>)

Recorded evaluation configuration: {"Method":"QLoRA","Evaluation Protocol":"Q2 Generative","Number of seeds":"5"}. This record does not assert independent reproduction.

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