Generating Fact Checking Briefs

TL;DR

This paper proposes a method to improve fact checking accuracy and efficiency by providing natural language briefs, especially Question-Answering Briefs generated by a new model, QABriefer, which enhances crowdworker performance.

Contribution

It introduces QABriefer, a novel model for generating question-answering briefs, and a new dataset, QABriefDataset, to improve fact checking processes.

Findings

QABriefs increase crowdworker accuracy by 10%.

QABriefs reduce fact checking time by around 20%.

Passage and entity briefs also improve accuracy.

Abstract

Fact checking at scale is difficult -- while the number of active fact checking websites is growing, it remains too small for the needs of the contemporary media ecosystem. However, despite good intentions, contributions from volunteers are often error-prone, and thus in practice restricted to claim detection. We investigate how to increase the accuracy and efficiency of fact checking by providing information about the claim before performing the check, in the form of natural language briefs. We investigate passage-based briefs, containing a relevant passage from Wikipedia, entity-centric ones consisting of Wikipedia pages of mentioned entities, and Question-Answering Briefs, with questions decomposing the claim, and their answers. To produce QABriefs, we develop QABriefer, a model that generates a set of questions conditioned on the claim, searches the web for evidence, and generates answers. To train its components, we introduce QABriefDataset which we collected via crowdsourcing. We show that fact checking with briefs -- in particular QABriefs -- increases the accuracy of crowdworkers by 10% while slightly decreasing the time taken. For volunteer (unpaid) fact checkers, QABriefs slightly increase accuracy and reduce the time required by around 20%.