What do Deep Networks Like to Read?

Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori. We propose Susceptibility Identification through Fine-Tuning (SIFT), a novel abstractive method that uncovers a model's preferences without imposing any prior... (read more)

Results in Papers With Code
(↓ scroll down to see all results)