QA-NatVer: Question Answering for Natural Logic-based Fact Verification

Fact verification systems assess a claim's veracity based on evidence. An important consideration in designing them is faithfulness, i.e. generating explanations that accurately reflect the reasoning of the model. Recent works have focused on natural logic, which operates directly on natural language by capturing the semantic relation of spans between an aligned claim with its evidence via set-theoretic operators. However, these approaches rely on substantial resources for training, which are only available for high-resource languages. To this end, we propose to use question answering to predict natural logic operators, taking advantage of the generalization capabilities of instruction-tuned language models. Thus, we obviate the need for annotated training data while still relying on a deterministic inference system. In a few-shot setting on FEVER, our approach outperforms the best baseline by 4.3 accuracy points, including a state-of-the-art pre-trained seq2seq natural logic system, as well as a state-of-the-art prompt-based classifier. Our system demonstrates its robustness and portability, achieving competitive performance on a counterfactual dataset and surpassing all approaches without further annotation on a Danish verification dataset. A human evaluation indicates that our approach produces more plausible proofs with fewer erroneous natural logic operators than previous natural logic-based systems. Janet Leigh was incapable of writing Janet Leigh was incapable was incapable of writing Janet Leigh was incapable of writing Janet Leigh She also wrote four books Janet Leigh She also wrote four She also wrote four books Janet Leigh She also wrote four books NatOp Assignment via QA (Sec. 3.2) Is was incapable of writing a negation of She also wrote four books? Proof Selection (Sec. 3.3) Janet Leigh was incapable of writing was incapable of writing