FEVER: a large-scale dataset for Fact Extraction and VERification

TL;DR

FEVER introduces a large-scale, challenging dataset for fact verification from Wikipedia-derived claims, aiming to advance research in automated claim verification and evidence retrieval.

Contribution

The paper presents FEVER, a new extensive dataset for fact verification, including annotated evidence, and evaluates baseline pipeline approaches to highlight its difficulty.

Findings

Best claim verification accuracy with evidence: 31.87%

Claim labeling accuracy without evidence: 50.91%

Dataset challenges current verification models

Abstract

In this paper we introduce a new publicly available dataset for verification against textual sources, FEVER: Fact Extraction and VERification. It consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from. The claims are classified as Supported, Refuted or NotEnoughInfo by annotators achieving 0.6841 in Fleiss $\kappa$. For the first two classes, the annotators also recorded the sentence(s) forming the necessary evidence for their judgment. To characterize the challenge of the dataset presented, we develop a pipeline approach and compare it to suitably designed oracles. The best accuracy we achieve on labeling a claim accompanied by the correct evidence is 31.87%, while if we ignore the evidence we achieve 50.91%. Thus we believe that FEVER is a challenging testbed that will help stimulate progress on claim verification against textual sources.