Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification

TL;DR

This paper proposes a multi-granular rationale extraction method for explainable multi-hop fact verification, ensuring consistency and faithfulness by training token- and sentence-level explainers simultaneously with differentiable masking.

Contribution

It introduces a novel approach for multi-granular rationale extraction that maintains consistency and faithfulness, improving interpretability in multi-hop fact verification models.

Findings

Outperforms state-of-the-art baselines on three datasets

Ensures rationales are faithful and consistent

Enhances interpretability of multi-hop fact verification models

Abstract

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising the veracity prediction. Although extensively explored, existing approaches fall within the scope of the single-granular (tokens or sentences) explanation, which inevitably leads to explanation redundancy and inconsistency. To address such issues, this paper explores the viability of multi-granular rationale extraction with consistency and faithfulness for explainable multi-hop fact verification. In particular, given a pretrained veracity prediction model, both the token-level explainer and sentence-level explainer are trained simultaneously to obtain multi-granular rationales via differentiable masking. Meanwhile, three diagnostic properties (fidelity, consistency, salience) are introduced and applied to the training process, to ensure that the extracted rationales satisfy faithfulness and consistency. Experimental results on three multi-hop fact verification datasets show that the proposed approach outperforms some state-of-the-art baselines.