Few-shot or zero-shot fact verification only relies on a few or no labeled training examples. In this paper, we propose a novel method called ProToCo, to \underline{Pro}mpt pre-trained language models (PLMs) \underline{To} be \underline{Co}nsistent, for improving the factuality assessment capability of PLMs in the few-shot and zero-shot settings. Given a claim-evidence pair, ProToCo generates multiple variants of the claim with different relations and frames a simple consistency mechanism as constraints for making compatible predictions across these variants. We update PLMs by using parameter-efficient fine-tuning (PEFT), leading to more accurate predictions in few-shot and zero-shot fact verification tasks. Our experiments on three public verification datasets show that ProToCo significantly outperforms state-of-the-art few-shot fact verification baselines. With a small number of unlabeled instances, ProToCo also outperforms the strong zero-shot learner T0 on zero-shot verification. Compared to large PLMs using in-context learning (ICL) method, ProToCo outperforms OPT-30B and the Self-Consistency-enabled OPT-6.7B model in both few- and zero-shot settings.

翻译：少样本或零样本事实验证仅依赖少量或无标注训练样例。本文提出名为ProToCo的新方法，通过提示预训练语言模型保持一致性，提升其在少样本和零样本场景下的事实评估能力。对于给定声明-证据对，ProToCo生成具有不同关系的多个声明变体，并将简单一致性机制作为约束条件，使这些变体间的预测结果相互兼容。我们采用参数高效微调更新预训练语言模型，从而在少样本和零样本事实验证任务中实现更精准的预测。在三个公开验证数据集上的实验表明，ProToCo显著优于当前最优的少样本事实验证基线方法。仅使用少量无标注实例，ProToCo在零样本验证中亦超越强零样本学习器T0。相较于基于上下文学习的预训练语言模型，ProToCo在少样本与零样本场景中均优于OPT-30B及采用自一致性机制的OPT-6.7B模型。