Czlc Rouge Raw

---
name: czlc-rouge-raw
description: Compute CZLC/rouge_raw via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of CZLC/rouge_raw.
metadata:
  skill_kind: metric
  source_lib: huggingface-evaluate
  hf_module: CZLC/rouge_raw
  source: library_introspection
---

# czlc-rouge-raw

> Metric `CZLC/rouge_raw` from the HuggingFace `evaluate` library.

## When to invoke

User asks to compute `CZLC/rouge_raw` or wants HF evaluate's canonical version.

## Recipe

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

## Don'ts

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