Defending Against Disinformation Attacks in Open-Domain Question Answering

arXiv:2212.10002v3 Announce Type: replace
Abstract: Recent work in open-domain question answering (ODQA) has shown that adversarial poisoning of the search collection can cause large drops in accuracy for production systems. However, little to no work has proposed methods to defend against these attacks. To do so, we rely on the intuition that redundant information often exists in large corpora. To find it, we introduce a method that uses query augmentation to search for a diverse set of passages that could …

abstract accuracy adversarial arxiv attacks collection cs.cl cs.ir disinformation domain intuition production question question answering search systems type work