FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information

TL;DR

FEVEROUS introduces a comprehensive dataset and benchmark for fact verification that incorporates both unstructured text and structured table data from Wikipedia, addressing limitations of previous benchmarks focused solely on text.

Contribution

The paper presents a novel dataset and benchmark combining textual and tabular evidence for fact verification, along with bias mitigation efforts and a baseline model.

Findings

Dataset contains 87,026 verified claims with evidence from text and tables.

Baseline model achieves 18% accuracy in predicting correct evidence and verdict.

Efforts to reduce dataset biases to prevent models from exploiting superficial cues.

Abstract

Fact verification has attracted a lot of attention in the machine learning and natural language processing communities, as it is one of the key methods for detecting misinformation. Existing large-scale benchmarks for this task have focused mostly on textual sources, i.e. unstructured information, and thus ignored the wealth of information available in structured formats, such as tables. In this paper we introduce a novel dataset and benchmark, Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS), which consists of 87,026 verified claims. Each claim is annotated with evidence in the form of sentences and/or cells from tables in Wikipedia, as well as a label indicating whether this evidence supports, refutes, or does not provide enough information to reach a verdict. Furthermore, we detail our efforts to track and minimize the biases present in the dataset and could be exploited by models, e.g. being able to predict the label without using evidence. Finally, we develop a baseline for verifying claims against text and tables which predicts both the correct evidence and verdict for 18% of the claims.