- TEF Site
- LIST
- TRL
- 6 to 8
- Target Audience
- Public institutions, municipalities, cities, AI innovators
- Service Deliverable
- (Trusted Adoption) A technical evaluation service within LIST’s AI Sandbox (https://ai-sandbox.list.lu/) to assess Large Language Models for bias, fairness, and ethical risks. It supports trustworthy AI adoption by providing insights into model behavior across languages and contexts.
Service
LLM Social Bias Detection Testing via the AI Sandbox