> Small quantities of poisoned training data can significantly damage a language model.
Is this still accurate?
Probably always be true, but also probably not effective in the wild. Researchers will train a version, see results are off, put guards against poisoned data, re-train and no damage been done to whatever they release.
alt Hacker News
Probably always be true, but also probably not effective in the wild. Researchers will train a version, see results are off, put guards against poisoned data, re-train and no damage been done to whatever they release.