ProoFVer: Natural Logic Theorem Proving for Fact Verification

TL;DR

ProoFVer introduces a natural logic-based proof system for fact verification that provides faithful, explainable inferences, achieving high accuracy and robustness, and improving human interpretability over existing methods.

Contribution

It presents ProoFVer, a novel seq2seq model that generates natural logic proofs for fact verification, enhancing explainability and robustness over neural classifiers.

Findings

Achieves highest label accuracy on FEVER dataset

Improves robustness by 13.21% on counterfactual data

Provides explanations that align better with human rationales

Abstract

Fact verification systems typically rely on neural network classifiers for veracity prediction which lack explainability. This paper proposes ProoFVer, which uses a seq2seq model to generate natural logic-based inferences as proofs. These proofs consist of lexical mutations between spans in the claim and the evidence retrieved, each marked with a natural logic operator. Claim veracity is determined solely based on the sequence of these operators. Hence, these proofs are faithful explanations, and this makes ProoFVer faithful by construction. Currently, ProoFVer has the highest label accuracy and the second-best Score in the FEVER leaderboard. Furthermore, it improves by 13.21% points over the next best model on a dataset with counterfactual instances, demonstrating its robustness. As explanations, the proofs show better overlap with human rationales than attention-based highlights and the proofs help humans predict model decisions correctly more often than using the evidence directly.