#subliminal-learning

[ follow ]
Data science
fromTheregister
17 hours ago

Bad teacher bots can leave hidden marks on model students

Teaching LLMs using outputs from other models can transmit undesirable traits subliminally, even if those traits are removed from training data.
Artificial intelligence
fromInfoWorld
8 months ago

Subliminal learning: When AI models learn what you didn't teach them

Fine-tuned models can inherit traits from base models despite efforts to filter data, requiring stricter safety evaluations.
[ Load more ]