English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Question answering models commonly have access to two sources of "knowledge"during inference time: (1) parametric knowledge - the factual knowledge encodedin the model weights, and (2) contextual knowledge - external knowledge (e.g.,a Wikipedia passage) given to the model to generate a grounded answer. Havingthese two sources of knowledge entangled together is a core issue forgenerative QA models as it is unclear whether the answer stems from the givennon-parametric knowledge or not. This unclarity has implications on issues oftrust, interpretability and factuality. In this work, we propose a new paradigmin which QA models are trained to disentangle the two sources of knowledge.Using counterfactual data augmentation, we introduce a model that predicts twoanswers for a given question: one based on given contextual knowledge and onebased on parametric knowledge. Our experiments on the Natural Questions datasetshow that this approach improves the performance of QA models by making themmore robust to knowledge conflicts between the two knowledge sources, whilegenerating useful disentangled answers.

DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering