模型与应用评测
How do you set up an evaluation framework from scratch for a new LLM application?
原题Your model passes one fairness metric but fails another. How do you handle conflicting audit results?
原题Your model was fair at deployment, but became biased 6 months later. How do you monitor continuously?
原题An external auditor cannot reproduce your model's results. How do you ensure audit reproducibility?
原题How do you structure red teaming for an LLM chatbot before launch?
原题How do you red team a multimodal model where text-only safety tests miss cross-modal attacks?
原题
暂无题目