ConceptAI & ML
Mitigations for hallucinations
Strategies used during training and inference, such as knowledge-based refusals or tool integration, to reduce the frequency of hallucinated model outputs.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.