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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

NLP systems have shown impressive performance at answering questions byretrieving relevant context. However, with the increasingly large models, it isimpossible and often undesirable to constrain models' knowledge or reasoning toonly the retrieved context. This leads to a mismatch between the informationthat the models access to derive the answer and the information that isavailable to the user to assess the model predicted answer. In this work, westudy how users interact with QA systems in the absence of sufficientinformation to assess their predictions. Further, we ask whether adding therequisite background helps mitigate users' over-reliance on predictions. Ourstudy reveals that users rely on model predictions even in the absence ofsufficient information needed to assess the model's correctness. Providing therelevant background, however, helps users better catch model errors, reducingover-reliance on incorrect predictions. On the flip side, backgroundinformation also increases users' confidence in their accurate as well asinaccurate judgments. Our work highlights that supporting users' verificationof QA predictions is an important, yet challenging, problem.

What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems