Improving Data Annotation for Low-Resource Relation Extraction with Logical Rule-Augmented Collaborative Language Models

Low-resource relation extraction aims to identify semantic relationships between entities using scarce labeled data. Recent studies exploit large language models to recognize relations based on retrieved examplars, yielding promising results. However, the reliability of predictions from these methods is constrained by the presence of irrelevant context within demonstrations and the inherent flaws of large language models in producing undesired outputs. Inspired by the precision and generalization of abstract logic, in this paper, we propose distilling logical rules to uniformly represent task knowledge sourced from distinct origins and facilitate deductive reasoning. We develop a collaborative annotating framework that iteratively integrates high-confidence predictions of rule-enhanced relation extractors with varying scales, efficiently obtaining reliable pseudo annotations from massive unlabeled samples without human supervision. Experiments under two inference settings show that our approach achieves new state-of-the-art performance on benchmark datasets in few-shot scenarios.