An Arabic evaluation dataset probes language-model trustworthiness across several risk categories.
- Category
- Datasets & benchmarks
- Type
- TRUST BENCHMARK
- Country / maker
- asas-ai
- Pricing
- Free
- Research paper published
- 14 Mar 2024
- Item last updated
- Not documented yet
- Added to Souq
- 26 Oct 2026
Capabilities
- trustworthiness evaluationsource (opens in a new tab on huggingface.co)
- risk category probingsource (opens in a new tab on huggingface.co)
- commonsense knowledge testingsource (opens in a new tab on huggingface.co)
- ethics and work ethics assessmentsource (opens in a new tab on huggingface.co)
- hallucination detection(unverified)
Supported languages
- Modern Standard Arabicsource (opens in a new tab on huggingface.co)
Site last checked: 12 Nov 2026
Details reviewed against the official source. Verification limits are noted in the description; items marked “unverified” are inferred only.
Official links
Official website — huggingface.co (opens in a new tab on huggingface.co)Related tools
© 2026 Souq. Original text and design: all rights reserved. Third-party trademarks and source material belong to their respective owners.