LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
This work aims to provide interpretable fact verification for users who need to understand why a claim is deemed true or false, addressing a limitation of existing neural models.
This paper addresses the problem of fact verification against large-scale textual knowledge sources. The authors propose LOREN, a model that decomposes claim verification at the phrase level, representing phrase veracity as three-valued latent variables regularized by logical rules, achieving competitive performance on a public benchmark.
Given a natural language statement, how to verify its veracity against a large-scale textual knowledge source like Wikipedia? Most existing neural models make predictions without giving clues about which part of a false claim goes wrong. In this paper, we propose LOREN, an approach for interpretable fact verification. We decompose the verification of the whole claim at phrase-level, where the veracity of the phrases serves as explanations and can be aggregated into the final verdict according to logical rules. The key insight of LOREN is to represent claim phrase veracity as three-valued latent variables, which are regularized by aggregation logical rules. The final claim verification is based on all latent variables. Thus, LOREN enjoys the additional benefit of interpretability -- it is easy to explain how it reaches certain results with claim phrase veracity. Experiments on a public fact verification benchmark show that LOREN is competitive against previous approaches while enjoying the merit of faithful and accurate interpretability. The resources of LOREN are available at: https://github.com/jiangjiechen/LOREN.