Defending Against Disinformation Attacks in Open-Domain Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909120627474432 |
|---|---|
| author | Weller, Orion Khan, Aleem Weir, Nathaniel Lawrie, Dawn Van Durme, Benjamin |
| author_facet | Weller, Orion Khan, Aleem Weir, Nathaniel Lawrie, Dawn Van Durme, Benjamin |
| contents | 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 answer the original question but are less likely to have been poisoned. We integrate these new passages into the model through the design of a novel confidence method, comparing the predicted answer to its appearance in the retrieved contexts (what we call Confidence from Answer Redundancy, i.e. CAR). Together these methods allow for a simple but effective way to defend against poisoning attacks that provides gains of nearly 20% exact match across varying levels of data poisoning/knowledge conflicts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_10002 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Defending Against Disinformation Attacks in Open-Domain Question Answering Weller, Orion Khan, Aleem Weir, Nathaniel Lawrie, Dawn Van Durme, Benjamin Computation and Language Information Retrieval 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 answer the original question but are less likely to have been poisoned. We integrate these new passages into the model through the design of a novel confidence method, comparing the predicted answer to its appearance in the retrieved contexts (what we call Confidence from Answer Redundancy, i.e. CAR). Together these methods allow for a simple but effective way to defend against poisoning attacks that provides gains of nearly 20% exact match across varying levels of data poisoning/knowledge conflicts. |
| title | Defending Against Disinformation Attacks in Open-Domain Question Answering |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2212.10002 |