PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts
PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts
A key component of modern conversational systems is the Dialogue State Tracker (or DST), which models a userās goals and needs. Toward building more robust and reliable DSTs, we introduce a prompt-based learning approach to automatically generate effective adversarial examples to probe DST models. Two key characteristics of this approach ā¦