James Chua
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect
According to the abstract, Clarke, Dubinski, Chua and colleagues report that poisoned fine-tuning data with no effect alone can create a hidden backdoor, such as misalignment, once clean data lacking a trigger feature is added to the training set.