Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence

TL;DR

VitaminC is a new benchmark dataset for fact verification that emphasizes subtle evidence differences, enhancing model robustness against changing information and supporting multiple related tasks.

Contribution

The paper introduces VitaminC, a challenging fact verification benchmark with contrastive evidence pairs, and demonstrates its effectiveness in improving model robustness and enabling auxiliary fact-checking tasks.

Findings

Training on VitaminC improves adversarial verification accuracy by 10%.

The dataset enhances robustness in natural language inference tasks.

Additional tasks like word tagging and revision detection are enabled by VitaminC.

Abstract

Typical fact verification models use retrieved written evidence to verify claims. Evidence sources, however, often change over time as more information is gathered and revised. In order to adapt, models must be sensitive to subtle differences in supporting evidence. We present VitaminC, a benchmark infused with challenging cases that require fact verification models to discern and adjust to slight factual changes. We collect over 100,000 Wikipedia revisions that modify an underlying fact, and leverage these revisions, together with additional synthetically constructed ones, to create a total of over 400,000 claim-evidence pairs. Unlike previous resources, the examples in VitaminC are contrastive, i.e., they contain evidence pairs that are nearly identical in language and content, with the exception that one supports a given claim while the other does not. We show that training using this design increases robustness -- improving accuracy by 10% on adversarial fact verification and 6% on adversarial natural language inference (NLI). Moreover, the structure of VitaminC leads us to define additional tasks for fact-checking resources: tagging relevant words in the evidence for verifying the claim, identifying factual revisions, and providing automatic edits via factually consistent text generation.