Multilingual Safety Eval

---
name: multilingual-safety-eval
description: Evaluates a parameter-efficient multilingual safety guardrail's ability to classify content as safe or unsafe across high-resource and low-resource languages. It probes cross-lingual generalization and robustness against diverse harm categories using cluster-guided transfer. Use when the user wants to benchmark on Aegis-Content-Safety-2.0-Test (Aegis-CS2), HarmBench, Redteam2k, JBB-Behaviors, StrongReject, or asks about evaluating this task. Reports accuracy.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2512.02711
  bibtex_key: bansal2025crest
  confidence: high
---

# multilingual-safety-eval

> CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer — Bansal et al. (2025) (arXiv:2512.02711, 2025)

## What this evaluates

Evaluates a parameter-efficient multilingual safety guardrail's ability to classify content as safe or unsafe across high-resource and low-resource languages. It probes cross-lingual generalization and robustness against diverse harm categories using cluster-guided transfer.

## Datasets

- **Aegis-Content-Safety-2.0-Test (Aegis-CS2)** — total ?; splits: test (-1)
- **HarmBench** — total ?; splits: test (-1)
- **Redteam2k** — total ?; splits: test (-1)
- **JBB-Behaviors** — total ?; splits: test (-1)
- **StrongReject** — total ?; splits: test (-1)

## Metrics

- `accuracy` **(primary)** — range: [0, 1]
  - Standard binary classification accuracy: the proportion of correctly classified safe/unsafe instances out of the total test instances.

## Input / output format

**Input**: Natural language prompts or conversation turns in 24 languages (13 In-Domain, 11 Out-of-Domain), representing human-LLM interactions or red-teaming queries.

**Output**: Binary classification label (safe vs. unsafe) produced by a single-layer classification head.

## Scoring recipe

```python
def compute_accuracy(predictions, gold_labels):
    correct = sum(1 for p, g in zip(predictions, gold_labels) if p == g)
    return correct / len(gold_labels)
```

## Common pitfalls

- Evaluating on Out-of-Domain (OOD) low-resource languages requires careful handling of translation artifacts, as training data was translated from English to In-Domain languages.
- Benchmarks cover diverse harm categories (hate, sexual, violence, etc.), so aggregate scores may mask per-category performance gaps.
- Cross-lingual transfer relies on linguistic clustering; performance may drop sharply for languages outside the 100-language XLM-R pretraining coverage.

## Evidence (verbatim from paper)

> For evaluation, we benchmark our model on six safety classification datasets: Aegis-Content-Safety-2.0-Test (Aegis-CS2) (2025), HarmBench (Mazeika et al. 2024), Redteam2k (Luo et al. 2024), JBB-Behaviors (subsets Behaviors as JBB-Behav and Judge-comparison as JBB-Judge) (Chao et al. 2024), and StrongReject (Souly et al. 2024). These benchmarks collectively span various harm categories, including but not limited to Hate/Identity Hate, Sexual, Suicide/Self-Harm, Violence, Guns/Illegal Weapons, PII/Privacy, Sexual Minor, Toxicity, Abuse, etc., which makes them suitable for a comprehensive evaluation of safety guardrails.

## Citation

```bibtex
@misc{bansal2025crest,
  title={CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer},
  author={Bansal et al. (2025)},
  year={2025},
  note={arXiv:2512.02711}
}
```

- arXiv: 2512.02711