Eric Wallace

Posts

Sorted by New

Wiki Contributions

Comments

Sorted by

You also may want to checkout Universal Adversarial Triggers https://arxiv.org/abs/1908.07125, which is an academic paper from 2019 that does the same thing as the above, where they craft the optimal worst-case prompt to feed into a model. And then they use the prompt for analyzing GPT-2 and other models.

This is cool! You may also be interested in Universal Triggers https://arxiv.org/abs/1908.07125. These are also short nonsense phrases that wreck havoc on a model.