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

Information-seeking questions in long-form question answering (LFQA) oftenprove misleading due to ambiguity or false presupposition in the question.While many existing approaches handle misleading questions, they are tailoredto limited questions, which are insufficient in a real-world setting withunpredictable input characteristics. In this work, we propose PreWoMe, aunified approach capable of handling any type of information-seeking question.The key idea of PreWoMe involves extracting presuppositions in the question andexploiting them as working memory to generate feedback and action about thequestion. Our experiment shows that PreWoMe is effective not only in tacklingmisleading questions but also in handling normal ones, thereby demonstratingthe effectiveness of leveraging presuppositions, feedback, and action forreal-world QA settings.

PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering