Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence

TL;DR

This paper introduces ReRead, a fact verification model that enhances evidence retrieval and claim verification by training retrievers for faithfulness and plausibility, leading to improved accuracy in real-world fact verification tasks.

Contribution

The paper presents a novel approach that jointly trains evidence retrievers and claim verifiers to produce faithful and plausible evidence, improving verification accuracy.

Findings

Significant performance improvements over existing models.

Effective evidence retriever trained for interpretability.

Enhanced claim verification accuracy.

Abstract

Real-world fact verification task aims to verify the factuality of a claim by retrieving evidence from the source document. The quality of the retrieved evidence plays an important role in claim verification. Ideally, the retrieved evidence should be faithful (reflecting the model's decision-making process in claim verification) and plausible (convincing to humans), and can improve the accuracy of verification task. Although existing approaches leverage the similarity measure of semantic or surface form between claims and documents to retrieve evidence, they all rely on certain heuristics that prevent them from satisfying all three requirements. In light of this, we propose a fact verification model named ReRead to retrieve evidence and verify claim that: (1) Train the evidence retriever to obtain interpretable evidence (i.e., faithfulness and plausibility criteria); (2) Train the claim verifier to revisit the evidence retrieved by the optimized evidence retriever to improve the accuracy. The proposed system is able to achieve significant improvements upon best-reported models under different settings.