Darrenchensformer Eval Keyphrase

---
name: darrenchensformer-eval-keyphrase
description: Compute DarrenChensformer/eval_keyphrase via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of DarrenChensformer/eval_keyphrase.
metadata:
  skill_kind: metric
  source_lib: huggingface-evaluate
  hf_module: DarrenChensformer/eval_keyphrase
  source: library_introspection
---

# darrenchensformer-eval-keyphrase

> Metric `DarrenChensformer/eval_keyphrase` from the HuggingFace `evaluate` library.

## When to invoke

User asks to compute `DarrenChensformer/eval_keyphrase` or wants HF evaluate's canonical version.

## Recipe

```python
import evaluate
metric = evaluate.load("DarrenChensformer/eval_keyphrase")
result = metric.compute(predictions=preds, references=refs)
print(result)
```

## Don'ts

- Don't assume your in-house `DarrenChensformer/eval_keyphrase` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.